检索结果-内蒙古大学图书馆

IEEE Transactions on Radar Systems 2025年 3卷 44-56页

作者： Kahya, Sabri Mustafa Yavuz, Muhammet Sami Steinbach, Eckehard Technical University of Munich Media Technology School of Computation Information and Technology Department of Computer Engineering Munich80333 Germany

Detecting human presence indoors with millimeter-wave frequency-modulated continuous-wave (FMCW) radar faces challenges from both moving and stationary clutters. This work proposes a robust and real-time capable human presence and out-of-distribution (OOD) detection method using 60-GHz short-range FMCW radar. HOOD solves the human presence and OOD detection problems simultaneously in a single pipeline. Our solution relies on a reconstruction-based architecture and works with radar macro- and micro-range-Doppler images (RDIs). HOOD aims to accurately detect the presence of humans in the presence or absence of moving and stationary disturbers. Since HOOD is also an OOD detector, it aims to detect moving or stationary clutters as OOD in humans' absence and predicts the current scene's output as "no presence."HOOD performs well in diverse scenarios, demonstrating its effectiveness across different human activities and situations. On our dataset collected with a 60-GHz short-range FMCW radar with only one transmit (Tx) and three receive antennas, we achieved an average area under the receiver operating characteristic curve (AUROC) of 94.36%. Additionally, our extensive evaluations and experiments demonstrate that HOOD outperforms state-of-the-art (SOTA) OOD detection methods in terms of common OOD detection metrics. Importantly, HOOD also perfectly fits on Raspberry Pi 3B+ with a advanced RISC machines (ARM) Cortex-A53 CPU, which showcases its versatility across different hardware environments. Videos of our human presence detection experiments are available at: https://***/HOOD. © 2023 IEEE.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

FedNAS: A Distributed Neural Architecture Search 2

FedNAS: A Distributed Neural Architecture Search

引用

2nd IEEE International Conference on Federated Learning Technologies and Applications, FLTA 2024

作者： Ramírez-Gordillo, Tamai Mora, Higinio Pujol, Francisco A. Maciá-Lillo, Antonio Department of Computer Technology and Computation University of Alicante Alicante Spain

ISBN: (纸本)9798350354812

In this paper, we present FedNAS, a distributed neural architecture search framework that integrates Federated Learning (FL) with Efficient Neural Architecture Search (ENAS) algorithm. This novel approach leverages the privacy-preserving capabilities of FL and the automated design optimization of NAS to collaboratively discover high-performance neural network architectures without sharing raw data. We propose a method wherein multiple clients independently execute the ENAS algorithm using local data and share their learned parameters with a central server. The server aggregates these parameters to create a global weight dictionary, facilitating knowledge transfer between clients and improving the overall model iteratively. We expect to demonstrate the potential of FedNAS by outlining its application to the CIFAR-10 dataset and discuss future work aimed at empirically validating the framework and comparing its performance against state-of-the-art architectures. Additionally, Blockchain technology will be integrated to enhance privacy and decentralization. ©2024 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Learning continuous network emerging dynamics from scarce observations via data-adaptive stochastic processes

引用

Science China(Information Sciences) 2024年第12期67卷 240-255页

作者： Jiaxu CUI Qipeng WANG Bingyi SUN Jiming LIU Bo YANG College of Computer Science and Technology Jilin University Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University Public Computer Education and Research Center Jilin University Department of Computer Science Hong Kong Baptist University

Learning network dynamics from the empirical structure and spatio-temporal observation data is crucial to revealing the interaction mechanisms of complex networks in a wide range of domains. However,most existing methods only aim at learning network dynamic behaviors generated by a specific ordinary differential equation instance, resulting in ineffectiveness for new ones, and generally require dense *** observed data, especially from network emerging dynamics, are usually difficult to obtain, which brings trouble to model learning. Therefore, learning accurate network dynamics with sparse, irregularly-sampled,partial, and noisy observations remains a fundamental challenge. We introduce a new concept of the stochastic skeleton and its neural implementation, i.e., neural ODE processes for network dynamics(NDP4ND), a new class of stochastic processes governed by stochastic data-adaptive network dynamics, to overcome the challenge and learn continuous network dynamics from scarce observations. Intensive experiments conducted on various network dynamics in ecological population evolution, phototaxis movement, brain activity, epidemic spreading, and real-world empirical systems, demonstrate that the proposed method has excellent data adaptability and computational efficiency, and can adapt to unseen network emerging dynamics, producing accurate interpolation and extrapolation with reducing the ratio of required observation data to only about 6% and improving the learning speed for new dynamics by three orders of magnitude.

关键词： complex networks network dynamics emerging spatio-temporal dynamics neural processes

来源：评论

学校读者我要写书评

暂无评论

SEOE:an option graph based semantically embedding method for prenatal depression detection

引用

Frontiers of computer Science 2024年第6期18卷 245-258页

作者： Xiaosong HAN Mengchen CAO Dong XU Xiaoyue FENG Yanchun LIANG Xiaoduo LANG Renchu GUAN College of Computer Science and Technology Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of EducationJilin UniversityChangchun 130012China Department of Electrical Engineering and Computer Science and Christopher S.Bond Life Sciences Center University of MissouriColumbiaMO 65211USA Department of Computer Science and Technology Zhuhai Laboratory of Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of EducationZhuhai College of Science and TechnologyZhuhai 519041China Jilin Provincial Institute of Population Science and Technology Changchun 130000China

Prenatal depression,which can affect pregnant women’s physical and psychological health and cause postpartum depression,is increasing ***,it is essential to detect prenatal depression early and conduct an attribution *** studies have used questionnaires to screen for prenatal depression,but the existing methods lack *** diagnose the early signs of prenatal depression and identify the key factors that may lead to prenatal depression from questionnaires,we present the semantically enhanced option embedding(SEOE)model to represent questionnaire *** can quantitatively determine the relationship and patterns between options and *** first quantifies options and resorts them,gathering options with little difference,since Word2Vec is highly dependent on *** resort task is transformed into an optimization problem involving the traveling salesman ***,all questionnaire samples are used to train the options’vector using ***,an LSTM and GRU fused model incorporating the cycle learning rate is constructed to detect whether a pregnant woman is suffering from *** verify the model,we compare it with other deep learning and traditional machine learning *** experiment results show that our proposed model can accurately identify pregnant women with depression and reach an F1 score of *** most relevant factors of depression found by SEOE are also verified in the *** addition,our model is of low computational complexity and strong generalization,which can be widely applied to other questionnaire analyses of psychiatric disorders.

关键词： questionnaire analyses text classification graph representation learning traveling salesman problem prenatal depression

来源：评论

学校读者我要写书评

暂无评论

Enhancing Answer Attribution for Faithful Text Generation with Large Language Models 16

Enhancing Answer Attribution for Faithful Text Generation wi...

引用

16th International Conference on Knowledge Discovery and Information Retrieval, KDIR 2024 as part of 16th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management, IC3K 2024

作者： Vladika, Juraj Mülln, Luca Matthes, Florian Technical University of Munich School of Computation Information and Technology Department of Computer Science Germany

ISBN: (纸本)9789897587160

The increasing popularity of Large Language Models (LLMs) in recent years has changed the way users interact with and pose questions to AI-based conversational systems. An essential aspect for increasing the trustworthiness of generated LLM answers is the ability to trace the individual claims from responses back to relevant sources that support them, the process known as answer attribution. While recent work has started exploring the task of answer attribution in LLMs, some challenges still remain. In this work, we first perform a case study analyzing the effectiveness of existing answer attribution methods, with a focus on subtasks of answer segmentation and evidence retrieval. Based on the observed shortcomings, we propose new methods for producing more independent and contextualized claims for better retrieval and attribution. The new methods are evaluated and shown to improve the performance of answer attribution components. We end with a discussion and outline of future directions for the task. © 2024 by SCITEPRESS – Science and technology Publications, Lda.

关键词： Question answering

来源：评论

学校读者我要写书评

暂无评论

State Representations as Incentives for Reinforcement Learning Agents: A Sim2Real Analysis on Robotic Grasping

State Representations as Incentives for Reinforcement Learni...

引用

2024 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2024

作者： Petropoulakis, Panagiotis Graf, Ludwig Malmir, Mohammadhossein Josifovski, Josip Knoll, Alois School of Computation Information and Technology Technical University of Munich Department of Computer Engineering Germany

ISBN: (纸本)9781665410205

Choosing an appropriate representation of the environment for the underlying decision-making process of the reinforcement learning agent is not always straightforward. The state representation should be inclusive enough to allow the agent to informatively decide on its actions and disentangled enough to simplify policy training and the corresponding sim2real transfer. Given this outlook, this work examines the effect of various representations in incentivizing the agent to solve a specific robotic task: antipodal and planar object grasping. A continuum of state representations is defined, starting from hand-crafted numerical states to encoded image-based representations, with decreasing levels of induced task-specific knowledge. The effects of each representation on the ability of the agent to solve the task in simulation and the transferability of the learned policy to the real robot are examined and compared against a model-based approach with complete system knowledge. The results show that reinforcement learning agents using numerical states can perform on par with non-learning baselines. Furthermore, we find that agents using image-based representations from pre-trained environment embedding vectors perform better than end-to-end trained agents, and hypothesize that separation of representation learning from reinforcement learning can benefit sim2real transfer. Finally, we conclude that incentivizing the state representation with task-specific knowledge facilitates faster convergence for agent training and increases success rates in sim2real robot control.22Supplementary materials can be found on the project webpage: https://***/PetropoulakisPanagiotis/igae © 2024 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

A Collocation-based Method for Addressing Challenges in Word-level Metric Differential Privacy 5

A Collocation-based Method for Addressing Challenges in Word...

引用

5th Workshop on Privacy in Natural Language Processing, PrivateNLP 2024 - Co-located with ACL 2024

作者： Meisenbacher, Stephen Chevli, Maulik Matthes, Florian Technical University of Munich School of Computation Information and Technology Department of Computer Science Garching Germany

ISBN: (纸本)9798891761391

Applications of Differential Privacy (DP) in NLP must distinguish between the syntactic level on which a proposed mechanism operates, often taking the form of word-level or document-level privatization. Recently, several word-level Metric Differential Privacy approaches have been proposed, which rely on this generalized DP notion for operating in word embedding spaces. These approaches, however, often fail to produce semantically coherent textual outputs, and their application at the sentence- or document-level is only possible by a basic composition of word perturbations. In this work, we strive to address these challenges by operating between the word and sentence levels, namely with collocations. By perturbing n-grams rather than single words, we devise a method where composed privatized outputs have higher semantic coherence and variable length. This is accomplished by constructing an embedding model based on frequently occurring word groups, in which unigram words co-exist with bi- and trigram collocations. We evaluate our method in utility and privacy tests, which make a clear case for tokenization strategies beyond the word level. © 2024 Association for computational Linguistics.

关键词： Differential privacy

来源：评论

学校读者我要写书评

暂无评论

Thinking Outside of the Differential Privacy Box: A Case Study in Text Privatization with Language Model Prompting

Thinking Outside of the Differential Privacy Box: A Case Stu...

引用

2024 Conference on Empirical Methods in Natural Language Processing, EMNLP 2024

作者： Meisenbacher, Stephen Matthes, Florian Technical University of Munich School of Computation Information and Technology Department of Computer Science Garching Germany

ISBN: (纸本)9798891761643

The field of privacy-preserving Natural Language Processing has risen in popularity, particularly at a time when concerns about privacy grow with the proliferation of Large Language Models. One solution consistently appearing in recent literature has been the integration of Differential Privacy (DP) into NLP techniques. In this paper, we take these approaches into critical view, discussing the restrictions that DP integration imposes, as well as bring to light the challenges that such restrictions entail. To accomplish this, we focus on DP-PROMPT, a recent method for text privatization leveraging language models to rewrite texts. In particular, we explore this rewriting task in multiple scenarios, both with DP and without DP. To drive the discussion on the merits of DP in NLP, we conduct empirical utility and privacy experiments. Our results demonstrate the need for more discussion on the usability of DP in NLP and its benefits over non-DP approaches. © 2024 Association for computational Linguistics.

关键词： Differential privacy

来源：评论

学校读者我要写书评

暂无评论

A Comparative Analysis of Word-Level Metric Differential Privacy: Benchmarking The Privacy-Utility Trade-off 30

A Comparative Analysis of Word-Level Metric Differential Pri...

引用

Joint 30th International Conference on computational Linguistics and 14th International Conference on Language Resources and Evaluation, LREC-COLING 2024

作者： Meisenbacher, Stephen Nandakumar, Nihildev Klymenko, Alexandra Matthes, Florian Technical University of Munich TUM School of Computation Information and Technology Department of Computer Science Garching Germany

ISBN: (纸本)9782493814104

The application of Differential Privacy to Natural Language Processing techniques has emerged in relevance in recent years, with an increasing number of studies published in established NLP outlets. In particular, the adaptation of Differential Privacy for use in NLP tasks has first focused on the word-level, where calibrated noise is added to word embedding vectors to achieve "noisy" representations. To this end, several implementations have appeared in the literature, each presenting an alternative method of achieving word-level Differential Privacy. Although each of these includes its own evaluation, no comparative analysis has been performed to investigate the performance of such methods relative to each other. In this work, we conduct such an analysis, comparing seven different algorithms on two NLP tasks with varying hyperparameters, including the epsilon (Ε) parameter, or privacy budget. In addition, we provide an in-depth analysis of the results with a focus on the privacy-utility trade-off, as well as open-source our implementation code for further reproduction. As a result of our analysis, we give insight into the benefits and challenges of word-level Differential Privacy, and accordingly, we suggest concrete steps forward for the research field. © 2024 ELRA Language Resource Association: CC BY-NC 4.0.

关键词： Natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

On the Integration of Privacy-Enhancing Technologies in the Process of Software Engineering 26

On the Integration of Privacy-Enhancing Technologies in the ...

引用

26th International Conference on Enterprise Information Systems, ICEIS 2024

作者： Klymenko, Alexandra Meisenbacher, Stephen Favaro, Luca Matthes, Florian Technical University of Munich TUM School of Computation Information and Technology Department of Computer Science Garching Germany

ISBN: (纸本)9789897586927

The class of technologies known as Privacy-Enhancing Technologies (PETs) has been receiving rising attention in the academic sphere. In practice, however, the adoption of such technologies remains low. Beyond the actual implementation of a PET, it is not clear where along the process of software engineering PETs should be considered, and which activities must take place to facilitate their implementation. In this light, we aim to investigate the placement of PETs in the software engineering process, specifically from the perspective of privacy requirements engineering. To do this, we conduct a systematic literature review and interview 10 privacy experts, exploring the integration of PETs into the software engineering process, as well as identifying associated challenges along with their potential solutions. We systematize our findings in a unified process diagram that illustrates the roles and activities involved in the implementation of PETs in software systems. In addition, we map the identified solution concepts to the diagram, highlighting which stages of the software engineering process are vital in tackling the corresponding challenges and supporting the adoption of PETs. © 2024 by SCITEPRESS – Science and technology Publications, Lda.

关键词： Requirements engineering

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：