检索结果-内蒙古大学图书馆

12th International Conference on Advanced Computer Information Technologies, ACIT 2022

作者： Hrybkov, Serhii Seidykh, Olga Vlasenko, Lidia Lytvynov, Valerii National University of Food Technologies Department of Information Systems Kyiv Ukraine National University of Food Technologies Department of Informatics Kyiv Ukraine National University of Trade and Economics Department of Software Engineering and Cyber Security Kyiv Ukraine Institute of Mathematical Machines and Systems Problems of Nasu Research Department № 220 'Intelligent Information-analytical System' Kyiv Ukraine

ISBN: (数字)9781665410502

ISBN: (纸本)9781665466479

The paper offers a solution to an important scientific and applied problem of scheduling to complete the orders for the provision of services aimed at maintenance and support of computer networks and equipment. This problem is relevant for companies providing such services. The main idea is to form an effective schedule for the completion of orders, as well as to enable its modification in the shortest time when getting orders. The paper also proposes an evaluation function that takes into account bonuses for the timely completion of orders and penalties for the late ones. A combination of a genetic algorithm with the methods of additional improvement on the basis of local optimization is offered. It allows reducing the time for the construction of effective alternative variants of decisions and their estimation. The use of the proposed approach to combining algorithms allows creating and reconfiguring the schedule for the completion of orders in the operational mode in a short time, and optimization makes it possible to reduce the completion of orders by up to 20%. Thus, the application of the proposed approaches will allow effective distribution of tasks among performers and give an economic effect by reducing the time to complete all orders. © 2022 IEEE.

关键词： Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

Memory and Schema in Human-Generative Artificial Intelligence Interactions

Memory and Schema in Human-Generative Artificial Intelligenc...

引用

International Conference on Tools for Artificial Intelligence (ICTAI)

作者： Dimitrios P. Panagoulias Persephone Papatheodosiou Anastasios Bonakis Dimitrios Dikeos Maria Virvou George A. Tsihrintzis Department of Informatics University of Piraeus Piraeus Greece Department of Psychiatry Sleep Research Unit National and Kapodistrian University of Athens Athens Greece Second Department of Neurology National and Kapodistrian University of Athens Athens Greece Department of Informatics Lab of Software Engineering University of Piraeus Piraeus Greece Department of Informatics Lab of Pattern Recognition and Machine Learning - Multimedia Systems University of Piraeus Piraeus Greece

ISBN: (数字)9798331527235

ISBN: (纸本)9798331527242

In this paper, we explore memory and Schema through the lens of mathematical representation. By defining themes related to cognitive processes, we propose a compression algorithm that measures and retains important information of previous (historic) user-Generative AI interaction. Time and memory are interconnected via a decay mechanism, where context gets more abstract as time passes. At the same time, memories with thematic resemblance can be structured into Schemas using set theory, based on rules influenced by a maturity threshold. This threshold is determined by factors such as criticality, emotional-user interaction, and mass, which is the measure of the summation of related memories. Our approach reconstructs memories into reusable parameters and formulates Schemas, offering a foundation for more personalized and cost-effective human-GAI interactions.

关键词： Cognitive processes Set theory Artificial intelligence Compression algorithms Lenses

来源：评论

学校读者我要写书评

暂无评论

Thrilling AI-A novel, signal-based digital biomarker for diagnosing canine heart diseases

Thrilling AI-A novel, signal-based digital biomarker for dia...

引用

作者： Bisgin, Pinar Strube, Tom Henze, Jasmin Ljungvall, Ingrid Häggström, Jens Wess, Gerhard Stadler, Julia Schummer, Christoph Meister, Sven Howar, Falk Maria Fraunhofer Institute for Software and Systems Engineering Emil-Figge-Str. 91 Dortmund44227 Germany Department of Clinical Sciences University of Agricultural Sciences Uppsala Sweden Clinic of Small Animal Medicine University of Munich Munich Germany Boehringer Ingelheim Animal Health Ingelheim am Rhein Germany Department of Health Informatics Witten/Herdecke University Witten Germany Department in Software Engineering Technical University of Dortmund Dortmund Germany

Auscultation methods enable non-invasive diagnosis of diseases, e.g. of the heart, based on heartbeat sounds. Regular, early examinations using machine learning techniques could help to detect diseases at an early stage to prevent serious health conditions and then provide optimal therapy through continuous monitoring. There is already a lot of work on human data using AI algorithms to detect patterns in signals or images. However, there is hardly no work on detecting heart murmurs with digital such as Myxomatous Mitral Valve Disease. In this paper, we present a canine auscultation project that aims to provide a tool to establish a baseline of classification parameters from audio signals that could be used to monitor canine health status by analyzing deviations from this baseline. In the future, data analysis could also lead to prediction and early detection of other diseases. © 2022 by Walter de Gruyter Berlin/Boston.

关键词： Pattern recognition

来源：评论

学校读者我要写书评

暂无评论

A Distributed MAPE-K Framework for Self-Protective IoT Devices

A Distributed MAPE-K Framework for Self-Protective IoT Devic...

引用

SEAMS International Workshop on software engineering for Adaptive and Self-Managing systems, ICSE

作者： Michael Riegler Johannes Sametinger Michael Vierhauser LIT Secure and Correct Systems Lab Johannes Kepler University Linz Linz Austria Department of Business Informatics - Software Engineering Johannes Kepler University Linz Linz Austria

Internet of Things (IoT) devices have become ubiquitous in our everyday life, with security becoming an ever-growing issue as more and more cyber-attack incidents being reported, primarily due to deficiencies in existing security mechanisms. However, while, for example, cloud-based applications, or industrial automation systems of systems possess significant resources for monitoring health, and determining their status and correct behavior at runtime, IoT devices operate with limited hardware capabilities and under tight resource constraints, making monitoring, analysis, and response activities a challenging endeavor. Following the NIST Cybersecurity Framework, IoT devices need to identify, protect, detect, respond, and recover from cyber-attacks, unauthorized access, and other security threats. A common way to provide self-adaptation to changing conditions is the MAPE-K loop with four pivotal phases: Monitor, Analyze, Plan, and Execute. This paper presents DSec4IoT, a “Distributed MAPE-K Framework for Self-Protective IoT Devices”. Our framework leverages the idea of distributed MAPE-K patterns and establishes a model for managing and controlling Self-Protective IoT Devices. We evaluate our approach by simulating port scans and performing adaptation activities. Results have confirmed that DSec4IoT can be easily applied to detect and mitigate them.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Trustworthy Model Elements as Basis for Seamless Bim Collaboration

SSRN

引用

SSRN 2024年

作者： Paskaleva, Galina Mazak-Huemer, Alexandra Huemer, Christian TU Wien Institute of Information Systems Engineering Favoritenstr. 9-11 ViennaA-1040 Austria Johannes Kepler University Linz Department of Business Informatics - Software Engineering Altenberger Strasse 69 Science Park 3 LinzA-4040 Austria

Current applications of BIM in the Architecture engineering and Construction (AEC) industry require multiple stakeholders to collaborate on the same digital model over multiple project phases, sharing the responsibility for the same model element. This requires trust, both between the stakeholders and between each stakeholder and the BIM technology. Lack of trust often manifests as poor collaboration, model duplications and break-down of model continuity. In this work, we present a method for the introduction of trust into the digital twin of a built structure by creating trustworthy model elements. The source of trust can be any technical or legal requirement. Such trusted model elements can offer a formal guarantee that the corresponding requirement has been fulfilled. Furthermore, this guarantee can be renewed automatically after each update by any project stakeholder. Finally, we introduce a standardized workflow for the maintenance and update of already established trusted elements in a digital twin. © 2024, The Authors. All rights reserved.

关键词： Architectural design

来源：评论

学校读者我要写书评

暂无评论

Wheelchair Wheel Design with Transformable “Wheel-Leg” Configuration for Climbing Stairs and Various Surfaces

Wheelchair Wheel Design with Transformable “Wheel-Leg” Con...

引用

International Russian Smart Industry Conference (SmartIndustryCon)

作者： Islam Magomedov Timur Aygumov Anzor A. Kanametov Bissnes informatics Kadyrov Chechen state university Grozny Russia Department of software engineering computer technology and automated systems Dagestan State Technical University Dagestan Russia Department of Electronics and Digital Information Technologies Kabardino-Balkarian State University Nalchik Russia

ISBN: (数字)9798331511241

ISBN: (纸本)9798331511258

The dynamic and uneven terrain of our environment introduces complexity for locomotion vehicles to navigate easily across different settings. Wheelchairs belong to the category of vehicles that require locomotion across various uneven terrains, such as stairs and other partitions. Therefore, the aim of this work is to design a wheel that can travel through various environments without using complex mechanisms. This aim was achieved by creating a novel transformable wheel. This wheel can turn into a legged wheel without using a complex mechanism and, when unnecessary, transform back into a normal wheel. Several simulations were carried out to understand the design's capability to overcome obstacles. In this case, the stair was the obstacle, and the results illustrated that the wheel is capable of climbing stairs without serious issues. Different parameters, such as speed and force, were examined with various values. The results showed that the weight on the wheelchair plays a significant role in climbing. For instance, with lighter weight, the structure moves without major slipping. The roughness of the surface is also related to the wheelchair's ability to reach the top of the stairs. A finer depth of cuts on the surface of the stairs increases the chance of the legged wheel firmly gripping and moving up the stairs.

关键词： Shape Navigation Wheelchairs Wheels Rotors Transforms Stairs Surface roughness Rough surfaces Vehicle dynamics

来源：评论

学校读者我要写书评

暂无评论

Leading Agents or Stewards? Exploring Design Principles for Empowerment through Workplace Technologies 42

Leading Agents or Stewards? Exploring Design Principles for ...

引用

42nd International Conference on Information systems: Building Sustainability and Resilience with IS: A Call for Action, ICIS 2021 TREOs

作者： Gierlich-Joas, Maren Zieglmeier, Valentin Neuburger, Rahild Hess, Thomas Munich School of Management Ludwig-Maximilians-Universität Munich Germany Chair of Software and Systems Engineering TUM Department of Informatics Technical University of Munich Munich Germany

ISBN: (纸本)9781713893608

Workplace technologies lead to increasing levels of transparency for managers and employees. On the one hand, transparency facilitates novel styles of work, but on the other hand, it drives employee privacy concerns. Despite the technical possibilities to monitor employees, workforce demands empowerment leadership and challenges the assumptions from agency theory. Thus, following a design science research process and collaborating closely with the software provider SoftCo over three years, we aim to develop a suitable technical solution to the changing needs. We build on the knowledge base of stewardship theory, the concept of transparency, and existing market solutions. The design cycles are driven by literature search and empirical investigations, such as qualitative interviews at SoftCo. In this research-in-progress paper, we derive design requirements, design principles, and design features for digital leadership innovations that facilitate stewardship behavior and outline our further research agenda. © 2021 42nd International Conference on Information systems, ICIS 2021 TREOs: "Building Sustainability and Resilience with IS: A Call for Action". All Rights Reserved.

关键词： Transparency

来源：评论

学校读者我要写书评

暂无评论

Vehicle type recognition: a case study of MobileNetV2 for an image Classification task

引用

Procedia Computer Science 2024年 246卷 3947-3956页

作者： Dariusz Kobiela Jan Groth Michał Hajdasz Mateusz Erezman Gdańsk University of Technology Faculty of Electronics Telecommunications and Informatics Department of Software Engineering Gabriela Narutowicza 11/12 Gdańsk 80-233 Poland Gdańsk University of Technology Faculty of Electronics Telecommunications and Informatics Department of Algorithms and Systems Modelling Gabriela Narutowicza 11/12 Gdańsk 80-233 Poland Gdańsk University of Technology Faculty of Electronics Telecommunications and Informatics Gabriela Narutowicza 11/12 Gdańsk 80-233 Poland

The goal of the research was to demonstrate the full data science lifecycle through a use case of the MobileNetv2 model for vehicle image Classification task using various validation and test sets, each with different difficulty level. Diverse model variations were employed, each designed to recognize images of ground vehicles and classify them into one of five possible classes: car, truck, motorcycle, bicycle, or bus. In terms of validation accuracy, the highest results were obtained by the model trained with uniformly designed train and val sets (with data normalization and augmentation), where train set also contained validation set. This model also obtained the highest accuracy results on both test sets. The superiority of MODEL 3 BASELINE is confirmed by other metrics as well: test loss, f1-score, AUC and confusion matrices (for both test sets). Results between MODEL 1 BASELINE and MODEL 2 BASELINE differed according to the test set 1 and 2 and other metrics and it was not possible to declare the superiority of one method of datasets preparation over another (original class distribution [no data normalization and no data augmentation] versus uniformly designed [with data normalization and augmentation]). The article also presents challenges and findings - the problems, key issues, and their solutions that arose during the process of data collection and tagging, as well as the preparation and evaluation of the model.

关键词： Image Classification vehicle type recognition MobileNetV2 transfer learning data processing data acquisition

来源：评论

学校读者我要写书评

暂无评论

Analysis of Legged Wheels with Spring Suspension for Stair-Climbing Robotics

Analysis of Legged Wheels with Spring Suspension for Stair-C...

引用

International Russian Smart Industry Conference (SmartIndustryCon)

作者： Islam Magomedov Timur Aygumov Josè Luis Ordõnez-Avila Bissnes informatics Kadyrov Chechen state university Grozny Russia Department at of software engineering computer technology and automated systems Dagestan State Technical University Dagestan Russia Universidad Tecnol'ogica Centroamericana(UNITEC) San Pedro Sula Honduras

ISBN: (数字)9798331511241

ISBN: (纸本)9798331511258

The following article looked into legged wheels with spring suspension. The idea behind the work was to see how adding springs in various places and their stiffness would impact the robot's ability to navigate through stairs. Due to the unconventional appearance of legged wheels, they are not suitable for even terrain passage. Hence, the idea was to add springs to minimize shock occurrence each time a leg touches the even environment. It was also important to equip springs throughout the whole path. As the robot progresses through steps, a greater disturbance of the structure occurs. Two different ideas were tested. In the first scenario, springs were attached between the holder of the wheels and the main body. In the second scenario, springs were directly added to the legs. The extruded part of the leg was divided into two, and a spring was embedded between these two parts. Different values of spring stiffness were also examined. The results illustrated that the structure would go further by implementing springs in all four wheels or in the rear. However, the structure was tested only on an upward incline. With other setups, it might be different with the rearrangement of the springs. It was also noted that with higher stiffness of the springs, the structure became unstable. In the second scenario, results illustrated the slightest progress. For instance, when the front wheels' legs were modified, they showed better results. To understand the influence in more depth, further investigation of the problem must be conducted.

关键词： Legged locomotion Industries Navigation Service robots Electric shock Wheels Stairs Boundary conditions Springs

来源：评论

学校读者我要写书评

暂无评论

Detection of Adversarial Supports in Few-Shot Classifiers Using Self-Similarity and Filtering

Detection of Adversarial Supports in Few-Shot Classifiers Us...

引用

2021 International Workshop on Safety and Security of Deep Learning, SSDL 2021

作者： Tan, Yi Xiang Marcus Chong, Penny Sun, Jiamei Cheung, Ngai-Man Elovici, Yuval Binder, Alexander Information Systems Technology and Design Pillar Singapore University of Technology and Design Singapore Department of Software and Information Systems Engineering Ben-Gurion University of the Negev Be’er Sheva Israel Department of Informatics University of Oslo Norway ST Engineering-SUTD Cyber Security Laboratory

Few-shot classifiers excel under limited training samples, making them useful in applications with sparsely user-provided labels. Their unique relative prediction setup offers opportunities for novel attacks, such as targeting support sets required to categorise unseen test samples, which are not available in other machine learning setups. In this work, we propose a detection strategy to identify adversarial support sets, aimed at destroying the understanding of a few-shot classifier for a certain class. We achieve this by introducing the concept of self-similarity of a support set and by employing filtering of supports. Our method is attack-agnostic, and we are the first to explore adversarial detection for support sets of few-shot classifiers to the best of our knowledge. Our evaluation of the miniImagenet (MI) and CUB datasets exhibits good attack detection performance despite conceptual simplicity, showing high AUROC scores. We show that self-similarity and filtering for adversarial detection can be paired with other filtering functions, constituting a generalisable concept. © 2021 CEUR-WS. All rights reserved.

关键词： Machine 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：