检索结果-内蒙古大学图书馆

Indoor Uncertain Semantic Trajectory Similarity Join

Journal of Computer Science & Technology 2024年第6期39卷 1441-1465页

作者： Hong-Bo Yin Dong-Hua Yang Kai-Qi Zhang Hong Gao Jian-Zhong Li Faculty of Computing Harbin Institute of TechnologyHarbin 150001China Center of Analysis Measurement and ComputingHarbin Institute of TechnologyHarbin 150001China Faculty of Computer Science and Control Engineering Shenzhen Institute of Advanced TechnologyChinese Academy of SciencesShenzhen 518055China

With the widespread deployment of indoor positioning systems, an unprecedented scale of indoor trajectories is being produced. By considering the inherent uncertainties and the text information contained in such an indoor trajectory, a new definition named Indoor Uncertain Semantic Trajectory is defined in this paper. In this paper, we focus on a new primitive, yet quite essential query named Indoor Uncertain Semantic Trajectory Similarity Join (IUST-Join for short), which is to match all similar pairs of indoor uncertain semantic trajectories from two sets. IUST-Join targets a number of essential indoor applications. With these applications in mind, we provide a purposeful definition of an indoor uncertain semantic trajectory similarity metric named IUS. To process IUST-Join more efficiently, both an inverted index on indoor uncertain semantic trajectories named 3IST and the first acceleration strategy are proposed to form a filtering-and-verification framework, where most invalid pairs of indoor uncertain semantic trajectories are pruned at quite low computation cost. And based on this filtering-and-verification framework, we present a highly-efficient algorithm named Indoor Uncertain Semantic Trajectory Similarity Join Processing (USP for short). In addition, lots of novel and effective acceleration strategies are proposed and embedded in the USP algorithm. Thanks to these techniques, both the time complexity and the time overhead of the USP algorithm are further reduced. The results of extensive experiments demonstrate the superior performance of the proposed work.

关键词： filtering-and-verification framework indoor uncertain semantic trajectory inverted index trajectory similarity join

来源：评论

学校读者我要写书评

暂无评论

Qualitative Comparison of Vision and Vision-Language Models in Object Detection: Capabilities and Challenges 29

Qualitative Comparison of Vision and Vision-Language Models ...

引用

29th International Conference on Information Technology, IT 2025

作者： Rakic, Branka Dejanovic, Igor University of Novi Sad Faculty of Technical Sciences Department of Computing and Control Engineering Serbia

ISBN: (纸本)9798331517649

Advancements in deep learning and computer vision have greatly enhanced object detection, playing a vital role in applications such as autonomous driving and surveillance. This study explores the trade-offs between two distinct YOLO model architectures: the vision-only models, referred to as pre-YOLO-World, and a vision-language model known as YOLO-World. While the pre-YOLO-World models are renowned for their speed and accuracy, the YOLO-World model integrates large language models to enhance contextual comprehension, enabling open-vocabulary object detection. This paper provides a qualitative analysis of their strengths and limitations, focusing on speed, accuracy, adaptability, computational requirements, and application scenarios. By contrasting these architectures, we aim to offer insights into their potential roles in evolving object detection paradigms and to guide practitioners in selecting models suited to specific use cases. © 2025 IEEE.

关键词： Machine vision

来源：评论

学校读者我要写书评

暂无评论

Accidental Centralization: Pitfalls of Blockchain-Based Project Architectures 11

Accidental Centralization: Pitfalls of Blockchain-Based Proj...

引用

11th International Conference on Electrical, Electronic and computing Engineering, IcETRAN 2024

作者： Petrović, Veljko B. Dragan, Dinu Gajlć, Dušan B. University of Novi Sad Faculty of Technical Sciences Control and Computing Department Novi Sad Serbia

ISBN: (纸本)9798350386998

Making use of blockchain in complex projects in ways which scale and keep costs down can lead to very complex architectural patterns. The problem with such patterns is that it is very easy to set up a system that only seems decentralized but, in fact, operates under a degraded trust model or is even centralized in practice. Using a blockchain to implement a centralized system represents a grotesque waste of computational resources for no benefit at all. This paper analyzes several cases of such architectural malfunction and shows how degraded trust can occur, how to detect it, and how to respond to this issue. © 2024 IEEE.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

Person re-identification with transformers and image stacking 32

Person re-identification with transformers and image stackin...

引用

32nd Telecommunications Forum, TELFOR 2024

作者： Stojanovic, Dimitrije Pavkovic, Bogdan Cetic, Nenad University of Novi Sad Faculty of Technical Sciences Departmant of Computing and Control Engineering Novi Sad Serbia

ISBN: (纸本)9798350391053

Person re-identification (ReID) is increasingly important due to the expansion of surveillance cameras. ReID can effectively operate in various conditions, making it suitable for security, retail analytics, and smart city applications. We propose a transformer-based model, DeepChangeVIT-ReID, fine-tuned with triplet loss, using the DeepChange dataset. We address long-term ReID challenges, including pose variations, camera angle differences, and clothing alterations. DeepChangeVIT-ReID achieves state-of-the-art performance, significantly improving Rank-1 accuracy compared to existing methods on the DeepChange dataset. © 2024 IEEE.

关键词： Distribution transformers

来源：评论

学校读者我要写书评

暂无评论

User Input Search - Custom Motion Estimation Algorithm Optimized for UAVs 46

User Input Search - Custom Motion Estimation Algorithm Optim...

引用

46th ICT and Electronics Convention, MIPRO 2023

作者： Benjak, J. Hofman, D. Faculty of Electrical Engineering and Computing Department of Control and Computer Engineering Zagreb Croatia

ISBN: (纸本)9789532331042

Unmanned aerial vehicle technology is growing rapidly as it finds its application in the various industries, including military & defense, agriculture, logistics, transportation, healthcare, entertainment and many others. One of the fastest growing industries including drones is the entertainment industry. More specifically, First Person View (FPV) piloting has become a popular sport which attracts huge masses. In FPV systems, the pilot wears FPV goggles and controls the drone using a controller, and the drone transmits video data to the goggles in real time. Since drones usually fly very quickly, the video quality in terms of resolution, compression artefacts and end-to-end delay must be maintained. This paper explores the idea of optimizing the Motion Estimation (ME) algorithm of existing High Efficiency Video Coding (HEVC) algorithms by utilizing user input from the controller. For example, if the drone is directed to hover to the left, then it would make sense to search for the most similar blocks in the previous video frame only on the left side of the referent block. For the purpose of this research, a HEVC video coder was customized to receive additional input besides the video data - the user input from the controller, or in other words, drone movement directions. We call this ME algorithm User Input Search (UIS). Our UIS algorithm is compared with the standard ME algorithms and its efficiency is tested. © 2023 MIPRO Croatian Society.

关键词： Real time systems

来源：评论

学校读者我要写书评

暂无评论

control Aspects in Programming by Demonstation for Robotic Deep- Micro- Hole Drilling 32

Control Aspects in Programming by Demonstation for Robotic D...

引用

32nd Mediterranean Conference on control and Automation, MED 2024

作者： Maric, Bruno Petric, Frano Orsag, Matko University of Zagreb LARICS Laboratory for Robotics and Intelligent Control Systems Faculty of Electrical Engineering and Computing Zagreb10000 Croatia

ISBN: (纸本)9798350395440

This paper explores control aspects in a collab-orative robotic system designed to replicate human operators' drilling skills in deep- micro- hole tasks, focusing on the glass-container mould industry. To replicate human performance, we develop a single-DOF Impedance-based drill controller for a standard industrial position-controlled robot, enhancing safe and smooth interactions between the drill bit and the mould. To address high feed rates observed in worker demonstrations and prevent bit breaks, we focus on minimizing non-axial motion during drilling on an off-the-shelf available industrial manipulator KUKA KR 10. This involves analyzing the impact of joint dynamics on drill motion and designing a control system for the robot's low-level control to achieve axial drill motion. We show that the proposed joint control system that takes into account relationship between joint and tool dynamics outperforms available robot low-level control in minimizing non-axial motion, leading to the robot being able to outperform the human in deep- micro- hole drilling. © 2024 IEEE.

关键词： Molds

来源：评论

学校读者我要写书评

暂无评论

A proposal of Android services generator for inter-connection with ADAS

A proposal of Android services generator for inter-connectio...

引用

2023 IEEE Zooming Innovation in Consumer Technologies Conference, ZINC 2023

作者： Boskovic, Ognjen Kokinovic, Aleksandar Kenjic, Dusan Kastelan, Ivan University of Novi Sad Faculty of Technical Science Department of Computing and Control Engineering Novi Sad Serbia

ISBN: (纸本)9798350347722

The integration of software in the automotive industry has become increasingly complex and time-sensitive, necessitating the implementation of efficient tools. One such tool is the utilization of a generator. Over the past decade, the implementation of In-Vehicle-Infotainment systems has become ubiquitous, occupying a central position within vehicles. Another system present in vehicles is the Advanced Driver Assistance System. Despite their prevalence, these systems operate in isolation. However, the utilization of Android services and a service-client architecture can facilitate communication between disparate systems through the implementation of various service-client-based protocols. This study proposes the development of a generator for Android services that enable communication between Advanced Driver Assistance System systems through the use of CommonAPI proxy. The implementation of this generator will expedite the production process of code that integrates these independent systems. © 2023 IEEE.

关键词： Advanced driver assistance systems

来源：评论

学校读者我要写书评

暂无评论

One solution of providing ADAS data to the IVI domain via the Android Java service

One solution of providing ADAS data to the IVI domain via th...

引用

2023 IEEE Zooming Innovation in Consumer Technologies Conference, ZINC 2023

作者： Stanisic, Dusan Antic, Marija Kenjic, Dusan Bilac, Luka University of Novi Sad Faculty of Technical Sciences Department of Computing and Control Engineering Novi Sad Serbia

ISBN: (纸本)9798350347722

In recent years, manufacturers are working parallel in developing and integrating two in-vehicle systems, an Advanced Driver Assistance System (ADAS) and In-Vehicle Infotainment (IVI). ADAS's purpose is to increase safety and aid the driver while the vehicle is in motion, by using various sensors to perceive the vehicle surrounding or the driver's errors and respond accordingly. Consumer applications in the IVI domain would significantly benefit from accessing such vehicle-specific data. Unfortunately, due to active vehicle system architecture requirements, the IVI domain cannot achieve communication with the ADAS by following traditional signal-oriented mechanisms. In addition, Android paved its way into the IVI domain as the most common Operating System because of its high flexibility and customization, but without being adapted for communication with ADAS. This paper offers a solution for enabling Android applications to access ADAS data via Java services. Data is procured over GENIVI company's SOME/IP-based communication middleware, integrated within the services. Communication performance is measured, evaluated, and limitations are identified. © 2023 IEEE.

关键词： Advanced driver assistance systems

来源：评论

学校读者我要写书评

暂无评论

Predicting Students’ Final Exam Scores Based on Their Regularity of Engagement with Pre-Class Activities in a Flipped Classroom 16

Predicting Students’ Final Exam Scores Based on Their Regul...

引用

16th International Conference on Computer Supported Education, CSEDU 2024

作者： Francišković, Teodor Sakal Anđelić, Ana Slivka, Jelena Luburić, Nikola Kovačević, Aleksandar Department of Computing and Control Engineering Faculty of Technical Sciences University of Novi Sad Trg Dositeja Obradovića 6 Novi Sad Serbia

ISBN: (纸本)9789897586972

Flipped Classroom (FC) is an active learning design requiring the students to engage in pre-class learning activities to prepare for face-to-face sessions. Identifying FC learning behaviors that lead to academic success remains a challenge. This paper addresses this challenge by conducting an empirical study in an undergraduate software engineering course employing the FC model. The empirical study draws on the data from an intelligent tutoring system that captured the learning traces of students performing pre-class activities. These traces provided indicators of students’ regularity of engagement, which were then matched to their final exam scores. Regression models were trained to predict final exam scores based on the regularity of engagement indicators. Students were clustered based on their regularity of engagement indicators to uncover actionable feedback for future course iterations. The case study confirms the generalizability of earlier findings that the regularity of engagement is vital for student performance and that course-specific predictors significantly impact the models’ prediction performance. Copyright © 2024 by Paper published under CC license (CC BY-NC-ND 4.0)

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Unit Test Generation Multi-Agent AI System for Enhancing Software Documentation and Code Coverage 32

Unit Test Generation Multi-Agent AI System for Enhancing Sof...

引用

32nd Telecommunications Forum, TELFOR 2024

作者： Stojanovic, Dimitrije Pavkovic, Bogdan Cetic, Nenad Krunic, Momcilo Vidakovic, Luka University of Novi Sad Faculty of Technical Sciences Departmant of Computing and Control Engineering Novi Sad Serbia LabSoft Novi Sad Serbia

ISBN: (纸本)9798350391053

Software development necessitates a robust testing plan though test development can be laborious and nonappealing task. We explore the utilization of the application artificial intelligence agents for generating and executing unit tests, enhancing the 'Mostly Basic Python Problems' dataset. We employ behavior-driven development within a three-agent system to generate user stories and unit tests. Empirical results indicate improvements in branch coverage, illustrating the effective utilization of large language models in software testing and development processes. © 2024 IEEE.

关键词： Software testing

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：