检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Jäger, Alex Kramer, Gerhard Institute of Communications Engineering Department of Computer Engineering School of Computation Information and Technology Technical University of Munich Munich80333 Germany

Joint detection and decoding (JDD) achieves rates based on information theory but is too complex to implement for many channels with memory or nonlinearities. Successive interference cancellation (SIC) at the receiver, combined with multistage encoding at the transmitter, is a method that lets one use coded modulation for memoryless channels to approach JDD rates. A SIC-based receiver is presented to compensate for inter-channel interference in long-haul optical fiber links. Simulations for 1000 km of standard single-mode fiber with ideal distributed Raman amplification, single-polarization transmission, and circularly symmetric complex Gaussian (CSCG) modulation show that SIC attains the achievable information rates (AIRs) of JDD using surrogate channel models with correlated phase and additive noise (CPAN). Moreover, the AIRs of ring constellations are compared to those of CSCG modulation. Simulations show that 32 rings, 16 SIC-stages, and Gaussian message passing on the factor graph of the CPAN surrogate model achieve the JDD rates of CSCG modulation. The computational complexity scales in proportion to the number of SIC-stages, where one stage has complexity similar to separate detection and decoding. Copyright © 2024, The Authors. All rights reserved.

关键词： Additive noise

来源：评论

学校读者我要写书评

暂无评论

Vision-driven Collaborative Mobile Robotic Human Assistant System for Daily Living Activities

引用

IFAC-PapersOnLine 2023年第2期56卷 4400-4405页

作者： Yuankai Wu Rayene Messaoud Xiao Chen Arne-Christoph Hildebrandt Marco Baldini Constantin Patsch Hamid Sadeghian Sami Haddadin Eckehard Steinbach Technical University of Munich School of Computation Information and Technology Department of Computer Engineering and Munich Institute of Robotics and Machine Intelligence (MIRMI) ABB

Assistive robotics is a rapidly growing research area. They are increasingly in demand in industry, medical services, or even domestic environments. Many assistance systems were developed in the last decades to help with industry tasks mainly. However, the majority of assistive robotic systems can only execute commands according to pre-defined instructions and are not capable of social interaction with humans. To this end, a human-centered assistive robotic system that can automatically assist or completely help humans to accomplish their intentions is expected. In this paper, we first proposed a novel triplet concept that describes the intended task of humans but will be executed by the assistive robot. The triplet includes target object, subject and action enabling the robot to identify auxiliary subjects, desired objects and perform required actions. Furthermore, a vision-driven mobile robotic human assistant system for assisting humans in daily life tasks is developed. The proposed triplet was proven to be able to complete a fully autonomous robotic system as a predefined input guide. Sensor calibration, deep learning based object detection, manipulation, and grasping techniques are used to achieve this goal. We evaluated the proposed system using various simulation and experimental scenarios and confirmed its effectiveness.

关键词： Autonomous robotic systems Human-centred automation and design Perception and sensing Assistive robot

来源：评论

学校读者我要写书评

暂无评论

Attribution rollout: a new way to interpret visual transformer

引用

Journal of Ambient Intelligence and Humanized Computing 2023年第1期14卷 163-173页

作者： Xu, Li Yan, Xin Ding, Weiyue Liu, Zechao College of Computer Science and Technology Harbin Engineering University Nantong Street Heilongjiang Harbin150001 China Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University Qianjin Street Jilin Changchun130012 China Department of Medicine Harvard Medical School Longwood Avenue BostonMA02115 United States

Transformer-based models are dominating the field of natural language processing and are becoming increasingly popular in the field of computer vision. However, the black box characteristics of transformers seriously hamper their application in certain fields. Prior work relies on the raw attention scores or employs heuristic propagation along with the attention graph. In this work, we propose a new way to visualize model. The method computes attention scores based on attribution and then propagates these attention scores through the layers. This propagation involves attention layers and multi-head attention mechanism. Our method extracts salient dependencies in each layer to visualize prediction results. We benchmark our method on recent visual transformer networks and demonstrate its many advantages over the existing interpretability methods. Our code is available at: https://***/yxheartipp/attr-rollout. © 2022, The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature.

关键词： Natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

RFOOD: Real-time Facial Authentication and Out -of-distribution Detection with Short-range FMCW Radar

RFOOD: Real-time Facial Authentication and Out -of-distribut...

引用

International Conference on Machine Learning and Applications (ICMLA)

作者： Sabri Mustafa Kahya Muhammet Sami Yavuz Boran Hamdi Sivrikaya Eckehard Steinbach Department of Computer Engineering Technical University of Munich School of Computation Information and Technology Chair of Media Technology Munich Institute of Robotics and Machine Intelligence (MIRMI)

ISBN: (数字)9798350374889

ISBN: (纸本)9798350374896

Out-of-distribution (OOD) detection is critical for the safe deployment of modern neural network architectures, as it aims to identify samples outside the training domain. In this paper, we introduce RFOOD, a novel OOD detection framework designed for real-time, privacy-preserving facial authentication using low-cost frequency-modulated continuous-wave (FMCW) radar. RFOOD employs both range-Doppler and micro range- Doppler images to enhance the detection accuracy. The architecture consists of a multi-encoder multi-decoder Body Part (BP) and Intermediate Linear Encoder-Decoder (ILED) components. This design allows the system to accurately classify a single individual's face as in-distribution (ID) while identifying all other faces as OOD. On our dataset collected with 60 GHz short-range FMCW radar, RFOOD achieves an Area Under the Receiver Operating Characteristic (AUROC) curve of 94.13 % and a False Positive Rate of 18.12% at a True Positive Rate of 95 % (FPR95). Additionally, RFOOD outperforms state-of-the-art OOD detection methods in common OOD detection metrics and operates in real-time.

关键词： Measurement Training Accuracy Neural networks Radar detection Authentication Receivers Feature extraction Real-time systems Faces

来源：评论

学校读者我要写书评

暂无评论

Long-Term Action Anticipation Based on Contextual Alignment

Long-Term Action Anticipation Based on Contextual Alignment

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Constantin Patsch Jinghan Zhang Yuankai Wu Marsil Zakour Driton Salihu Eckehard Steinbach Department of Computer Engineering Chair of Media Technology Munich Institute of Robotics and Machine Intelligence (MIRMI) School of Computation Information and Technology Technical University of Munich

In action anticipation, the model predicts the next future action after a certain observation period. In long-term action anticipation, this idea is further extended to predicting multiple actions and their respective duration. Thus, in this problem setting the model should not only capture relationships between past actions but also predict several future actions that fit into a certain context. Compared to autoregressive models, our model employs an encoder decoder structure to determine future actions and durations in parallel, which prevents the accumulation of prediction errors and reduces the inference time. Furthermore, it is ensured that the predicted actions are aligned with respect to a context representation, which resembles the way humans approach this task as the feasible action set is restricted by the respective context. We evaluate our model on the long-term anticipation benchmark datasets, Breakfast, and 50Salads, where we achieve state-of-the-art results.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Propagating Threat Scores with a TLS Ecosystem Graph Model Derived by Active Measurements

Propagating Threat Scores with a TLS Ecosystem Graph Model D...

引用

Network Traffic Measurement and Analysis Conference (TMA)

作者： Markus Sosnowski Patrick Sattler Johannes Zirngibl Tim Betzer Georg Carle Technical University of Munich Germany Department of Computer Engineering Chair of Network Architectures and Services TUM School of Computation Information and Technology

ISBN: (数字)9783903176645

ISBN: (纸本)9798350378887

The Internet is shaped by independent actors and heterogeneous deployments. With the wide adoption of Transport Layer Security (TLS), a whole ecosystem of intertwined entities emerged. Acquiring a comprehensive view allows searching for previously unknown malicious entities and providing valuable cyber-threat intelligence. Actively collected Internet-wide Domain Name System (DNS) and TLS meta-data can provide the basis for such large-scale analyses. However, in order to efficiently navigate the vast volumes of data, an effective methodology is required. This work proposes a graph model of the TLS ecosystem that utilizes the relationships between servers, domains, and certificates. A Probabilistic Threat Propagation (PTP) algorithm is then used to propagate a threat score from existing blocklists to related nodes. We conducted a one-year-long measurement study of 13 monthly active Internet-wide DNS and TLS measurements to evaluate the methodology. The latest measurement found four highly suspicious clusters among the nodes with high threat scores. External threat intelligence services were used to confirm a high rate of maliciousness in the rest of the newly found servers. With the help of optimized thresholds, we identified 557 domains and 11 IP addresses throughout the last year before they were known to be malicious. Up to 40% of the identified nodes appeared on average three months later on the input blocklist. This work proposes a versatile graph model to analyze the TLS ecosystem and a PTP analysis to help security researchers focus on suspicious subsets of the Internet when searching for unknown threats.

关键词： Analytical models Ecosystems Clustering algorithms Telecommunication traffic Data models Blocklists Internet

来源：评论

学校读者我要写书评

暂无评论

Initial Populations with a Few Heuristic Solutions Significantly Improve Evolutionary Multi-Objective Combinatorial Optimization

Initial Populations with a Few Heuristic Solutions Significa...

引用

2023 IEEE Symposium Series on computational Intelligence, SSCI 2023

作者： Gong, Cheng Nan, Yang Pang, Lie Meng Ishibuchi, Hisao Zhang, Qingfu Southern University of Science and Technology Guangdong Provincial Key Laboratory of Brain-inspired Intelligent Computation Department of Computer Science and Engineering Shenzhen518055 China City University of Hong Kong Department of Computer Science Kowloon Tong Hong Kong The City University of Hong Kong Shenzhen Research Institute Shenzhen China

ISBN: (纸本)9781665430654

Population initialization is a crucial and essential step in evolutionary multi-objective optimization (EMO) algorithms. The quality of the generated initial population can significantly affect the performance of an EMO algorithm. However, few studies have focused on designing a generalized initialization method to improve the performance of EMO algorithms in solving multi-objective combinatorial optimization (MOCO) problems. Most of the existing advanced initialization methods involve complex techniques tailored to the specific characteristics of the problems to be solved. In this paper, we propose a general and effective framework of population initialization for EMO algorithms, aiming to improve their performances in solving various MOCO problems. Our approach involves the inclusion of a few specific heuristic solutions, including extreme solutions and a center solution, into the initial population. This inclusion serves to guide the evolution of the population throughout the optimization process. Our experimental results show that initial populations with a few heuristic solutions significantly improve the performance of EMO algorithms. Algorithm behavior analysis and further study are also provided, allowing for a comprehensive understanding of the effectiveness and applicability of our proposed method. © 2023 IEEE.

关键词： Evolutionary multi-objective optimization algorithms Multi-objective combinatorial optimization Population initialization

来源：评论

学校读者我要写书评

暂无评论

NPRF: Neural Painted Radiosity Fields for Neural Implicit Rendering and Surface Reconstruction

NPRF: Neural Painted Radiosity Fields for Neural Implicit Re...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Driton Salihu Adam Misik Yuankai Wu Constantin Patsch Eckehard Steinbach Department of Computer Engineering Chair of Media Technology Munich Institute of Robotics and Machine Intelligence (MIRMI) Technical University of Munich School of Computation Information and Technology Siemens Technology

In recency, neural signed distance fields have become more popular for reconstructing 3D indoor environments. While great improvements have been made due to missing incident radiance and materials in the surface estimation, current methods cannot reconstruct high-quality surfaces. To address this issue, we propose Neural Painted Radiosity Fields (NPRF), consisting of Neural Radiosity Fields for volumetric surface representation and Neural Painted Scenes for novel view synthesis. Neural Radiosity Fields combine the radiative transfer equation with neural radiosity to estimate 3D surfaces, thus leveraging raytracing to improve the volumetric representation. Neural Painted Scenes employs sparsification and projection of 3D points into 2D images in conjunction with a generative, context-aware inpainting network to produce high-quality novel views. We show that NPRF leads to overall improvements in F-score on the popular ScanNet dataset. Finally, we show that NPRF improves novel view synthesis by a significant margin, giving improvements of up to 25% on PSNR, 53% on LPIPS, and 3% on SSIM.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Examination of the Multimodal Nature of Multi-Objective Neural Architecture Search

Examination of the Multimodal Nature of Multi-Objective Neur...

引用

2023 IEEE Symposium Series on computational Intelligence, SSCI 2023

ISBN: (纸本)9781665430654

Remarkable successes in deep learning have spurred significant growth in the field of neural architecture search (NAS), which is rapidly advancing as a promising technique for automating the design of network architecture. From an optimization standpoint, a NAS task for a given search space can be viewed as a multi-objective optimization problem (MOP) when considering multiple design criteria simultaneously (e.g., prediction accuracy, architecture complexity, hardware efficiency). However, whether a NAS problem is a multimodal multi-objective optimization problem or not (i.e., whether a single non-dominated solution in the objective space has multiple different neural network architectures or not) has not been examined in the literature. This presents an intriguing research question that merits further investigation. To fill this gap, we examine the multimodal nature of seven multi-objective NAS problems. By doing so, this work aims to help MOP researchers to better understand the characteristics of the multi-objective NAS problems. © 2023 IEEE.

关键词： Multi-objective optimization Multimodal multi-objective optimization Neural architecture search

来源：评论

学校读者我要写书评

暂无评论

DeepHBSP:A Deep Learning Framework for Predicting Human Blood-Secretory Proteins Using Transfer Learning

引用

Journal of computer Science & technology 2021年第2期36卷 234-247页

作者： Wei Du Yu Sun Hui-Min Bao Liang Chen Ying Li Yan-Chun Liang Key Laboratory of Symbol Computation and Knowledge Engineering of Ministry of Education College of Computer Science and TechnologyJilin UniversityChangchun 130012China Department of Computer Science College of EngineeringShantou UniversityShantou 515063China Zhuhai Laboratory of Key Laboratory of Symbol Computation and Knowledge Engineering of Ministry of Education Zhuhai College of Jilin University Zhuhai 519041China

The identification of blood-secretory proteins and the detection of protein biomarkers in the blood have an important clinical application *** methods for predicting blood-secretory proteins are mainly based on traditional machine learning algorithms,and heavily rely on annotated protein *** traditional machine learning algorithms,deep learning algorithms can automatically learn better feature representations from raw data,and are expected to be more promising to predict blood-secretory *** present a novel deep learning model(DeepHBSP)combined with transfer learning by integrating a binary classification network and a ranking network to identify blood-secretory proteins from the amino acid sequence information *** loss function of DeepHBSP in the training step is designed to apply descriptive loss and compactness loss to the binary classification network and the ranking network,*** feature extraction subnetwork of DeepHBSP is composed of a multi-lane capsule ***,transfer learning is used to train a highly accurate generalized model with small samples of blood-secretory *** main contributions of this study are as follows:1)a novel deep learning architecture by integrating a binary classification network and a ranking network is proposed,superior to existing traditional machine learning algorithms and other state-of-the-art deep learning architectures for biological sequence analysis;2)the proposed model for blood-secretory protein prediction uses only amino acid sequences,overcoming the heavy dependence of existing methods on annotated protein features;3)the blood-secretory proteins predicted by our model are statistically significant compared with existing blood-based biomarkers of cancer.

关键词： blood-secretory protein deep learning capsule network transfer learning

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：