检索结果-内蒙古大学图书馆

10th International Conference on Machine Learning, Optimization, and Data Science, LOD 2024

作者： Komini, Vangjush Girdzijauskas, Sarunas Qamcom Research and Technology AB Kistagången 12 Kista164 40 Sweden Kistagången 12 Kista164 40 Sweden RISE Kistagången 16 Kista164 40 Sweden

ISBN: (纸本)9783031824838

Deep learning (DL) models have significantly transformed machine learning (ML), particularly with their prowess in classification tasks. However, these models struggle to differentiate between in-distribution (ID) and out-of-distribution (OOD) data at the testing phase. This challenge has curtailed their deployment in sensitive fields like biotechnology, where misidentifying OOD data, such as unclear or unknown bacterial genomic sequences, as known ID classes could lead to dire consequences. To address this, we propose an approach to make DL models OOD-sensitive by exploiting the configuration of the logit space embeddings, into the model’s decision-making process. Leveraging the effect observed in recent studies that there is minimal overlap between the embeddings of ID and OOD data, we use a density estimator to model the ID logit distribution based on the training data. This allows us to reliably flag data that do not match the ID distribution as OOD. Our methodology is designed to be independent of the specific data or model architecture and can seamlessly augment existing trained models without the need to expose them to OOD data. Testing our method on widely recognized image datasets, we achieve leading-edge results, including a substantial 10% enhancement in the area under the receiver operating characteristic curve (AUCROC) on the Google genome dataset. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

Temporal Differential Privacy for Human Activity Recognition

Temporal Differential Privacy for Human Activity Recognition

引用

International Conference on Data Science and Advanced Analytics (DSAA)

作者： Debaditya Roy Šarūnas Girdzijauskas Royal Institute of Technology (KTH) Qamcom Research and Technology AB Stockholm Sweden

Differential privacy (DP) is a method to protect individual privacy when the data is used for downstream analytical tasks. The core ability of DP to quantity privacy numerically separates it from other privacy-preserving methods. In human activity recognition (HAR), differential privacy can protect users’ privacy who contribute their data to train machine learning algorithms. While some methods are developed for privacy protection in such cases, no method quantifies privacy and seamlessly integrates into machine learning frameworks like DP. The paper proposes a DP framework called TEMPDIFF (short for temporal differential privacy), which guarantees privacy preserving human activity recognition for wearable time-series data with competitive classification performance and works with any machine-learning/deep-learning methods. TEMPDIFF capitalizes on the temporal characteristics of wearable sensor data to improve the modelling task, which enhances the privacy-utility tradeoff. TEMPDIFF uses ensembling and a novel temporal partitioning algorithm for time-series data to ensure optimal training of ensemble models. In TEMPDIFF, consensus through ensembling and the addition of controlled Laplacian noise obscures sensitive information used to train the models, guaranteeing strict levels of differential privacy. The proposed method is evaluated on two popular HAR datasets. It outperforms the classification accuracy and privacy budget for both datasets compared to the state-of-the-art approaches.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Distributed MIMO Systems for 6G

Distributed MIMO Systems for 6G

引用

European Conference on Networks and Communications (EuCNC)

作者： Omer Haliloglu Han Yu Charitha Madapatha Hao Guo Fehmi Emre Kadan Andreas Wolfgang Rafael Puerta Pål Frenger Tommy Svensson Ericsson Research Türkiye Chalmers University of Technology Sweden Qamcom Research and Technology AB Sweden Ericsson Research Sweden

This study focuses on Distributed MIMO (D-MIMO) systems and provides a discussion about their role in next generation networks. The paradigm shift to distributed networks offers great potential to address the 6G requirements, through macro diversity. As 6G scenarios and use cases continue to emerge, new challenges are likely to arise that may affect the widespread imp-lementation of D-MIMO. To address those, different deployment options have been proposed for roll-out considerations. They are composed of several sub-components that can be categorized as (i) wireless or wired fronthaul/backhaul, (ii) analog or digital signals, (iii) distributed or centralized processing, and (iv) coherent or non-coherent transmission. To facilitate standardization efforts, we provide 3GPP-aligned terminology for network nodes, multi-point transmission and reception schemes. In order to enable large-scale implementation of D-MIMO systems, it is important to determine the needed amount of distribution, develop practical solutions for high-frequency bands, and ways to convey data that meet the transport requirements. On this regard, we discuss key enablers and present simulation results for D-MIMO systems towards 6G. In particular, we present solutions for D-MIMO networks in dynamic scenarios related to channel estimation and layer-l mobility considering coherent and non-coherent joint transmission, and analog fronthaul implementation using analog-radio-over-fiber that are promising for high (upper mm-Wave and (sub-)THz) carrier frequencies, as well as integrated access and backhaul, network-controlled repeaters, and reconfigurable intelligent surfaces that are possible enablers for cost-efficient network densification at both low (cm-Wave, lower mm-Wave) and high carrier frequencies.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Unified Taxonomy for Automated Vehicles: Individual, Cooperative, Collaborative, On-Road, and Off-Road

arXiv

引用

arXiv 2023年

作者： Warg, Fredrik Thorsén, Anders Vu, Victoria Bergenhem, Carl RISE Research Institutes of Sweden Borås Sweden Semcon Sweden AB Göteborg Sweden Qamcom Research and Technology AB Göteborg Sweden

Various types of vehicle automation is increasingly used in a variety of environments including road vehicles such as cars or automated shuttles, confined areas such as mines or harbours, or in agriculture and forestry. In many use cases, the benefits are greater if several automated vehicles (AVs) cooperate to aid each other reach their goals more efficiently, or collaborate to complete a common task. Taxonomies and definitions create a common framework that helps researchers and practitioners advance the field. However, most existing work focus on road vehicles. In this paper, we review and extend taxonomies and definitions to encompass individually acting as well as cooperative and collaborative AVs for both on-road and off-road use cases. In particular, we introduce classes of collaborative vehicles not defined in existing literature, and define levels of automation suitable for vehicles where automation applies to additional functions in addition to the driving task. Copyright © 2023, The Authors. All rights reserved.

关键词： Taxonomies

来源：评论

学校读者我要写书评

暂无评论

A Dual-Polarized Dual-Band Flat-Top Pattern 5G mm-Wave Array Antenna

A Dual-Polarized Dual-Band Flat-Top Pattern 5G mm-Wave Array...

引用

European Conference on Antennas and Propagation, EuCAP

作者： Johan Wettergren Xinxin Yang Per Landin Qamcom Research and Technology Göteborg Sweden Ericsson AB Kumla Sweden

A nine-element antenna array is presented. It has a flat-top radiation pattern and is matched for use in both the 24.25-29.5 GHz and the 37–40 GHz frequency bands for 5G mm-wave systems. The application of this anten... 详细信息

关键词： Resistors Base stations 5G mobile communication Breadboard Propagation losses Reflection Frequency measurement

来源：评论

学校读者我要写书评

暂无评论

Minimal Risk Manoeuvre Strategies for Cooperative and Collaborative Automated Vehicles

Minimal Risk Manoeuvre Strategies for Cooperative and Collab...

引用

International Conference on Dependable Systems and Networks Workshops (DSN-W)

作者： Victoria Vu Fredrik Warg Anders Thorsén Stig Ursing Fredrik Sunnerstam Jimmy Holler Carl Bergenhem Irina Cosmin Semcon Sweden AB Göteborg Sweden RISE Research Institutes of Sweden Borås Sweden Agreat AB Göteborg Sweden Epiroc Rock Drills AB Örebro Sweden Qamcom Research and Technology AB Göteborg Sweden

During the last decade, there has been significant increase in research focused on automated vehicles (AVs) and ensuring safe operation of these vehicles. However, challenges still remain, some involving the cooperation and collaboration of multiple AVs, including when and how to perform a minimal risk manoeuvre (MRM), leading to a minimal risk condition (MRC) when an AV within one of these systems is unable to complete its original goal. As most literature is focused on individual AVs, there is a need to adapt and extend the knowledge and techniques to these new contexts. Based on existing knowledge of individual AVs, this paper explores MRM strategies involving cooperative and collaborative AV systems with different capabilities. Specifically, collaborative systems have the potential to enact local MRCs, allowing continued productivity despite having one (or several) of its constituents encounter a fault. Definitions are provided for local and global MRCs, alongside discussions of their implications for MRMs. Illustrative examples are also presented for each type of system.

关键词：

来源：评论

学校读者我要写书评

暂无评论

On Perception Safety Requirements and Multi Sensor Systems for Automated Driving Systems

On Perception Safety Requirements and Multi Sensor Systems f...

引用

SAE 2020 World Congress Experience, WCX 2020

作者： Cassel, Anders Bergenhem, Carl Christensen, Ole Martin Heyn, Hans-Martin Leadersson-Olsson, Susanna Majdandzic, Mario Sun, Peng Thorsén, Anders Trygvesson, Jörgen Qamcom Research and Technology Ab Volvo Technology Ab Sweden Veoneer Sweden Ab Sweden Semcon Sweden Ab Sweden Rise Research Institutes of Sweden Sweden Comentor Ab

One major challenge in designing SAE level 3-5 Automated Driving Systems (ADS) is to define requirements for the perception system that would enable argumentation for safe operation. The safety requirements on the perception system can only be fulfilled through redundancy in the sensor hardware. It is, however, a challenge to specify the redundancy that is required in the sensor system. Safe operation for an ADS is significantly more difficult compared to advanced driver assistance systems (ADAS). The safety argumentation for ADAS typically argues that in case of a failure in the sensor array a fail-silent behavior is acceptable because the human driver can take control of the vehicle back. This argumentation however is not possible when developing level 4 or higher automation. This paper investigates prerequisites for applying a systematic methodology for analyzing redundancy in a multi-sensor system and the relation to a conceptual ADS functional architecture. This analysis must address the complexity that comes with partially overlapping sensor data from different sensors and considers variations in performance and characteristics due to changes in the environmental conditions. The paper introduces the term incomplete redundancy and presents a systematic methodology for analyzing redundancy. The aim is to provide arguments for how several sensors in a system, when appropriately combined, meet an assigned safety requirement on a higher level. Each sensor will then be assigned a certain responsibility and contributes with a sub-set of information. A set of questions of importance to address as a foundation for such a methodology are defined and discussed. The definitions of redundancy and independence between sensors are discussed as well as contract-based functional safety to adapt to different environmental and operating conditions. © 2020 SAE International. All Rights Reserved.

关键词： Redundancy

来源：评论

学校读者我要写书评

暂无评论

Path Assignment in Mesh Networks at the Edge of Wireless Networks

arXiv

引用

arXiv 2024年

作者： Kumar, Siddhartha Moghaddam, Mohammad Hossein Wolfgang, Andreas Svensson, Tommy Qamcom Research and Technology AB Gothenburg Sweden Catalytic Technology AB Gothenburg Sweden Chalmers University of Technology Gothenburg Sweden

We consider a mesh network at the edge of a wireless network that connects users to the core network via multiple base stations. For this scenario, we present a novel tree-search-based algorithm that strives to identify effective communication path to the core network for each user by maximizing the signal-to-noise-plus-interference ratio (SNIR) along the chosen path. We show that, for three mesh networks of varying sizes, our algorithm selects paths with minimum SNIR values that are 3 dB to 18 dB higher than those obtained through an algorithm that disregards interference within the network, 16 dB to 20 dB higher than those chosen randomly by a random path selection algorithm, and 0.5 dB to 7 dB higher compared to a recently introduced genetic algorithm (GA). Furthermore, we demonstrate that our algorithm has lower computational complexity compared to the GA in networks where its performance is within 2 dB of ours. © 2024, CC BY.

关键词： Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

6G Positioning and Sensing Through the Lens of Sustainability, Inclusiveness, and Trustworthiness

arXiv

引用

arXiv 2023年

作者： Wymeersch, Henk Chen, Hui Guo, Hao Keskin, Musa Furkan Khorsandi, Bahare M. Moghaddam, Mohammad H. Ramirez, Alejandro Schindhelm, Kim Stavridis, Athanasios Svensson, Tommy Yajnanarayana, Vijaya Department of Electrical Engineering Chalmers University of Technology Sweden Electrical and Computer Engineering Department New York University Tandon School of Engineering BrooklynNY United States Chalmers University of Technology Sweden Nokia Strategy and Technology Munich Germany QAMCOM Research and Technology AB Gothenburg Sweden Siemens’ corporate research unit in Munich Germany Ericsson Research Ericsson Sweden Ericsson Research India

6G promises a paradigm shift by integrating positioning and sensing, enhancing not only the communication performance but also enabling location- and context-aware services. Historically, positioning and sensing were focused on cost and performance tradeoffs, implying an escalated demand for resources, such as radio, physical, and computational resources, for improved performance. However, 6G expands this perspective, embracing a set of broader values, namely sustainability, inclusiveness, and trustworthiness. From a joint industrial/academic perspective, this paper aims to shed light on these important value indicators and their relationship with the conventional key performance indicators in the context of positioning and sensing. © 2023, CC BY.

关键词： Sustainable development

来源：评论

学校读者我要写书评

暂无评论

EMC challenges for the era of massive Internet of Things

引用

IEEE Electromagnetic Compatibility Magazine 2019年第2期8卷 65-74页

作者： Wiklundh, Kia Stenumgaard, Peter Qamcom Research and Technology AB Linköping Sweden Linköping Sweden

The technical development towards the full vision of the Internet of Things (IoT) is expected to reach its full potential by the coming 5G wireless technologies. This will open up for so called massive IoT characterized by very large co-location densities. This development will affect the area of Electromagnetic Compatibility (EMC) in a number of ways and may even be the most challenging issue for the EMC area since it was born for over 100 years ago. The challenges that emerge as a result of the mass increase of wirelessly consumer devices, dense co-located, working in new frequency bands and in scenarios characterized by being highly dynamic, flexible and non-predictable, will be complex and will require new EMC equipment, theoretical models and methodologies for EMC analysis and testing to be developed. In this paper, some of these new challenges are highlighted and discussed. Furthermore, numerical results from some dense co-location scenarios are presented to show examples of interference challenges to be handled. © 2012 IEEE.

关键词： Electromagnetic compatibility

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：