检索结果-内蒙古大学图书馆

Scanning the Issue – Sept 2024 Additional Papers

IEEE Transactions on Intelligent Transportation Systems 2024年第9期25卷 10457-10461页

作者： Simona Sacone Department of Computer Science Bioengineering Robotics and Systems Engineering University of Genova Genova Italy

Summary form only: Abstracts of articles that will be presented in future issues of this publication.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Enhanced Ship Classification in SAR Imagery using Fine-tuned DenseNet and Self-attention 15

Enhanced Ship Classification in SAR Imagery using Fine-tuned...

引用

15th International Conference on Computing Communication and Networking Technologies, ICCCNT 2024

作者： Chethan, Kosaraju Sai Lokesh, Vadlamudi Reddy, Kunta Vignaj Singh, Rimjhim Padam Srivastava, Smita Amrita Vishwa Vidyapeetham Amrita School of Computing Department of Computer Science and Engineering Bengaluru India Defense Research & Development Organization Centre for Artificial Intelligence & Robotics Bengaluru India

ISBN: (纸本)9798350370249

The categorization of ships in synthetic aperture radar (SAR) imagery is vital for civilian and military applications, including maritime management and reconnaissance. Deep learning techniques, such as Inception, DenseNet, Fusion Transformers, and EfficientNet, are used to extract multiscale information from SAR images, improving classification capabilities. Advanced solutions are necessary to address challenges in SAR imagery, such as speckle noise, varying illumination conditions, and complex sea clutter. The FUSAR-Ship dataset, which utilizes GF-3 SAR technology, offers a comprehensive collection of diverse scenarios including sea, land, coast, river, and islands. With over 5000 ship chips containing AIS messages and examples of various clutter types, FUSAR-Ship is a benchmark dataset for ship classification tasks. Our research involves thorough testing of advanced classification models using the FUSAR dataset. Through meticulous evaluation of a wide range of ship instances, scales, and maritime scenes, we aim to demonstrate the robustness and adaptability of these models. By refining their architectures and optimizing their parameters, we strive to enhance the capabilities of classification models and advance the performance of ship classification in SAR imagery. Our efforts contribute to enhancing maritime surveillance, management, and reconnaissance in both civilian and military domains. © 2024 IEEE.

关键词： DenseNet201 EfficientNetB1 InceptionV3 MobilenetV3Small RestNet50 Self Attention Ship small object detection Xception

来源：评论

学校读者我要写书评

暂无评论

Intelligent Accident Recognition and Notification System using Hybrid Deep Learning and IoT 4

Intelligent Accident Recognition and Notification System usi...

引用

4th International Conference on Soft Computing for Security Applications, ICSCSA 2024

作者： Sathish Kumar, P. Singh Rawat, Ramesh Shrimali, Manish Parikh, Swapnil Patil, Harshal Maranan, Ramya United Institute of Technology Department of Robotics & Automation Tamil Nadu Coimbatore641020 India Graphic Era Deemed to Be University Department of Computer Science & Engineering Uttarakhand Dehradun248 002 India Department of Computer Science and IT Rajasthan Udaipur313 003 India Parul Institute of Engineering and Technology Parul University Department of Computer Science and Engineering Gujarat 391760 India Symbiosis Institute of Technology Symbiosis International Deemed University Computer Science and Engineering Maharashtra Pune412 115 India Saveetha School of Engineering SIMATS Department of Research and Innovation Tamil Nadu Chennai602105 India

ISBN: (纸本)9798331515720

Ensuring the safety of individuals should be a top priority. Everyone wants to return home safely. Many riders continue to disregard safety constraints, increasing the chance of accidents that result in death. It is critical to incorporate the latest technology into road monitoring systems to make cities smarter and to ensure rider safety. For this research, Deep Learning (DL) and the Internet of Things (IoT) were chosen for effective road surveillance and alert systems. The primary goal of the study is to detect and inform riders about accidents that occur along their path and to provide details about the location of the detected accident. Additionally, the system provides the vehicle's speed. To identify automobile accidents in the footage, a hybrid DL model that includes Convolutional Neural Network-Bidirectional Long Short-Term Memory (CNN-Bi-LSTM) is suggested. For the model's training, both accident and non-Accident data were collected. The model is evaluated using three metrics: Accuracy, loss, and execution time. The next step is to upload the recommended model to the ThingSpeak cloud. A Graphical User Interface (GUI) is being created in the ThingSpeak cloud. The GUI displays the vehicle's speed, accident images, and the precise location of the accident scene using the Raspberry Pi, speed sensor, Pi-camera, and Global Positioning System (GPS) module. An LED is also integrated into the GUI to alert the user. A real-world test is conducted on the designed system. The proposed solution has many advantages and will ensure driver safety. © 2024 IEEE.

关键词： Graphical user interfaces

来源：评论

学校读者我要写书评

暂无评论

Network Parameter Control in Cellular Networks through Graph-Based Multi-Agent Constrained Reinforcement Learning 19

Network Parameter Control in Cellular Networks through Graph...

引用

19th IEEE International Conference on Automation science and engineering, CASE 2023

作者： Forsberg, Albin Larsson Nikou, Alexandros Feljan, Aneta Vulgarakis Tumova, Jana Stockholm Sweden Kth Division of Robotics Perception and Learning Department of Electrical Engineering and Computer Science Stockholm Sweden Digital Futures United States

ISBN: (纸本)9798350320695

Cellular networks are growing in complexity at increasing speed and the geographical locations in which they are deployed in are getting denser. Traditional control methods fall short in providing a scalable and dynamic way of adapting the network to new conditions. Distributed multiagent reinforcement learning successfully addresses scalability problems seen in centralized approaches. The question of achieving learning with constraint satisfaction in distributed systems is still left unanswered in the state-of-the-art. In this work, we aim to perform distributed multi-agent constrained reinforcement learning in order to learn a policy online while satisfying imposed constraints. We use a coordination graph to model the interactions between agents and decompose the global value function. A conservative safety critic is trained in parallel to evaluate the safety of proposed actions. Our method allows for separate training of both the critic and the value network independently of each other, and hence offers flexibility in how and when to train the different models. The results are compared to a baseline using no safety critic. Simulations show that the agents succeed in learning a policy that can satisfy the constraints, while still maximizing the objective. © 2023 IEEE.

关键词： Graphic methods

来源：评论

学校读者我要写书评

暂无评论

Social engineering attack types and prevention techniques- A survey 1

Social engineering attack types and prevention techniques- A...

引用

1st International Conference on Computational Intelligence, Communication Technology and Networking, CICTN 2023

作者： Salama, Ramiz Al-Turjman, Fadi Bhatia, Shruti Yadav, Satya Prakash Near East University Ai and Robotics Institute Research Center for Ai and IoT Department of Computer Engineering Nicosia Turkey Near East University Ai and Robotics Institute Artificial Intelligence Engineering Dept. Nicosia Turkey University of Kyrenia Research Center for Ai and IoT Faculty of Engineering Kyrenia Turkey Graphic Era Hill University Department of Computer Science and Engineering Dehradun India Department of Computer Science and Engineering Greater Noida201306 India

ISBN: (纸本)9798350338027

The term "Cyber Security"is getting more and more popular and important over the last few years. Since computers and most of the devices are connected to the internet, they are likely to be hacked by the hackers. In the past, this issue was not a big problem, because not every device is required to be connected to the internet or the internet was not popular as today. But the case has changed over the years. All the changes in the technology area also changed the cyber-attack models as well. With the development of technology and the change of usage of the internet over the last years cyber-attacks have become more common and popular by the hackers. Hackers have discovered that they have an opportunity to steal or earn money in a short time without having to spend too much effort. These days, the type of cyber-attacks is not the same as the ones in the past. As time passes, the cyber-attack methods are also changing and evolving. Today, hackers are using more advanced and effective cyber-attack methods compared to past years. There are many methods that are impossible to cover all of them in this article. Our main focus will be on social engineering attacks in this article. Social engineering attacks use different approaches to cyber attacking. Unlike trying to explode a victim's social media password etc. using advanced exporting programs, algorithms or techniques, social engineering attacks focus on fooling victims into providing their data to hackers by themselves without using or implementing any password cracking, exploiting techniques etc. We will go over what social media engineering is, type of social engineering methods, what countermeasures can be used to protect from social engineering and more in this article. © 2023 IEEE.

关键词： Crime

来源：评论

学校读者我要写书评

暂无评论

FaceEngine: A Tracking-Based Framework for Real-Time Face Recognition in Video Surveillance System

引用

SN computer science 2024年第5期5卷 609页

作者： Imran, Ahsan Ahmed, Riad Hasan, Md Mehedi Ahmed, M. Helal Uddin Azad, A.K.M. Alyami, Salem A. Department of Robotics and Mechatronics Engineering University of Dhaka Dhaka 1000 Bangladesh Department of Computer Science and Engineering BRAC University Dhaka 1212 Bangladesh Department of Management Information Systems University of Dhaka Dhaka 1000 Bangladesh Department of Mathematics and Statistics College of Science Imam Mohammad Ibn Saud Islamic University (IMSIU) Riyadh 11432 Saudi Arabia

The escalating concern over worldwide security and criminal activities has led to the emergence and significance of closed-circuit television video surveillance systems as an essential tool for diverse security purposes. These systems are extensively implemented and serve a crucial function in the surveillance and upkeep of security. The predominant purpose of video surveillance systems is to gather data primarily for evidentiary purposes subsequent to the occurrence of a criminal incident. The demand for video surveillance systems capable of autonomously monitoring and promptly identifying criminals or intruders in real-time is steadily increasing. Nevertheless, the existing facial recognition methods pose difficulties in reliably identifying individuals who are in motion within a video frame. Moreover, conventional approaches necessitate a substantial quantity of photographs in order to achieve precise recognition following the acquisition of an individual’s facial pattern. In order to tackle these concerns, we developed the implementation of input optimisation algorithms alongside a novel framework for real-time face recognition in the context of video surveillance. The input optimization algorithms, integrated with adaptive thresholding techniques, effectively reduce the need for manual outlier removal by actively identifying outliers for each specific case. The application of this optimisation strategy has demonstrated a substantial enhancement in both the efficiency and precision of our system in comparison to alternative baseline methodologies. Through the use of a reduced set of input image, our system is capable of attaining a heightened degree of improvements. Specifically, employing tracking and temporal voting techniques enables our system to accomplish a real-time face recognition accuracy of 90.91%. The findings of this study suggest that our approach has the potential to be a valuable tool in various applications that necessitate rapid and precise fac

关键词： computer vision Deep learning Face recognition Image processing Tracking Video surveillance

来源：评论

学校读者我要写书评

暂无评论

Exploiting Cross-Modal Cost Volume for Multi-sensor Depth Estimation 17th

Exploiting Cross-Modal Cost Volume for Multi-sensor Depth E...

引用

17th Asian Conference on computer Vision, ACCV 2024

作者： Kim, Janghyun Shin, Ukcheol Heo, Seokyong Park, Jinsun Department of Information Convergence Engineering Pusan National University Busan Korea Republic of Robotics Institute Carnegie Mellon University Pittsburgh United States School of Computer Science and Engineering Pusan National University Busan Korea Republic of

ISBN: (纸本)9789819609680

Single-modal depth estimation has shown steady improvement over the years. However, relying solely on a single imaging sensor such as RGB and near-infrared (NIR) cameras can result in unreliable and erroneous depth estimation, particularly in challenging lighting conditions such as low-light or sudden lighting change scenarios. Thereby, several approaches have leveraged multiple sensors for robust depth estimation. However, the effective fusion method that maximally utilizes multi-modal sensor information still requires further investigation. With this in mind, we propose a multi-modal cost volume fusion strategy with cross-modal attention, incorporating information from both cross-spectral and single-modality pairs. Our method initially constructs low-level cost volumes that consist of modality-specific (ı.e., single modality) and modality-invariant (ı.e., cross-spectral) volumes from multi-modal sensors. These cost volumes are then gradually fused using bidirectional cross-modal fusion and unidirectional LiDAR fusion to generate a multi-sensory cost volume. Furthermore, we introduce a straightforward domain gap reduction approach to learn modality-invariant features and depth refinement techniques through cost volume-guided propagation. Experimental results demonstrate that our method achieves SOTA (State-of-the-Art) performance under diverse environmental changes. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Depth perception

来源：评论

学校读者我要写书评

暂无评论

Squid-inspired and wirelessly controllable display for active camouflage in aquatic-environment

引用

npj Flexible Electronics 2024年第1期8卷 900-909页

作者： Doyoung Kim Seung Won Seon Minkyung Shin Jihwan Kim Bogeun Kim Janghoon Joo Sang Uk Park Wooseok Kim Hee Kyu Lee Byeong Woon Lee Se Gi Lee Su Eon Lee Ji-Hun Seo Seung Ho Han Bong Hoon Kim Sang Min Won Department of Electrical and Computer Engineering Sungkyunkwan University2066Seobu-roJangan-guSuwon 16419Republic of Korea Department of Smart Wearable Engineering Soongsil UniversitySeoul 06978Republic of Korea Electronic Convergence Materials and Devices Research Center Korea Electronics Technology Institute(KETI)Seongnam 13509Republic of Korea Department of Materials Science and Engineering Korea UniversitySeoul 02841Republic of Korea Department of Robotics and Mechatronics Engineering DGISTDaegu 42988Republic of Korea

Achieving optimal camouflage in an aquatic environment necessitates the ability to modulate transmittance in response to the surrounding obscurity and potential *** adaptation involves a dynamic transition from transparency to a deep-blue color,especially in low-light or dark *** a strategy promotes a seamless assimilation with the surroundings,enabling the absorption of searchlights and,subsequently,diminishing the risk of detection by ***,the presence of sophisticated mechanisms that facilitates stable and efficient control of transmittance is imperative,enabling smooth transition between transparent and deep-blue hues within the aquatic *** study presents nature-inspired programmable camouflage system that integrates an electrochromic display as the primary transmittance change element and a wireless base module for power and data *** technology offers a robust and flexible construction,ensuring stable operation as demonstrated through mechanical-fatigue experiments and quantitative simulation.A custom circuit and a power-control software package enable active control of multiple electrochromic displays while submerged in water.

关键词： transparency submerged lights

来源：评论

学校读者我要写书评

暂无评论

Finding Optimal Nash Equilibria in Multiplayer Games via Correlation Plans 22

Finding Optimal Nash Equilibria in Multiplayer Games via Cor...

引用

22nd International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2023

作者： Zhang, Youzhi An, Bo Subrahmanian, V.S. Centre for Artificial Intelligence and Robotics Hong Kong Institute of Science & Innovation CAS Hong Kong School of Computer Science and Engineering Nanyang Technological University Singapore Department of Computer Science Northwestern University Evanston United States

Designing efficient algorithms to compute a Nash Equilibrium (NE) in multiplayer games is still an open challenge. In this paper, we focus on computing an NE that optimizes a given objective function. Finding an optimal NE in multiplayer games can be formulated as a mixed-integer bilinear program by introducing auxiliary variables to represent bilinear terms, leading to a huge number of bilinear terms, making it hard to solve. To overcome this challenge, we propose a novel algorithm called CRM based on a novel mixed-integer bilinear program with correlation plans for some subsets of players, which uses Correlation plans with their Relations to strictly reduce the feasible solution space after the convex relaxation of bilinear terms while Minimizing the number of correlation plans to significantly reduce the number of bilinear terms. Experimental results show that our algorithm can be several orders of magnitude faster than the state-of-the-art baseline. © 2023 International Foundation for Autonomous Agents and Multiagent Systems (***). All rights reserved.

关键词： Computation theory

来源：评论

学校读者我要写书评

暂无评论

Retrospective of Kazakh-Russian Sign Language Corpus Formation 11

Retrospective of Kazakh-Russian Sign Language Corpus Formati...

引用

11th Workshop on the Representation and Processing of Sign Languages: Evaluation of Sign Language Resources, sign-lang@LREC-COLING 2024

作者： Imashev, Alfarabi Kydyrbekova, Aigerim Mukushev, Medet Sandygulova, Anara Islam, Shynggys Israilov, Khassan Makazhanov, Aibek Yessenbayev, Zhandos Department of Robotics Engineering Nazarbayev University Kazakhstan Computer Science Lab National Laboratory Astana Nazarbayev University Kazakhstan Public Association "Kazakh Deaf Society" Astana Branch Kazakhstan

ISBN: (纸本)9782493814302

Sign language (SL) is a mode of communication that, in most cases, relies on visual perception exclusively and uses the visual-gestural modality. The advent of machine learning techniques has expanded the range of potential applications, not only in industry but also in addressing societal needs. Previous research has already demonstrated encouraging outcomes in developing sign language recognition systems that are both quite accurate and resilient. Nevertheless, the effectiveness and use of algorithms are impacted not only by their accessibility but also, at times to a greater extent, by the presence of substantial quantities of pertinent data. At the start of the local sign language corpus collection in 2015, there was a notable deficit of local Kazakh-Russian Sign Language data available for computer vision and machine-learning tasks. There were already corpora of another lexically close language, Russian Sign Language, but they were aimed at and tailored for lingustic research. We initiated the procedure by collecting data appropriate for machine-learning purposes. The subsets have been incorporated into the principal corpus and will be subject to future enhancements and refinements. This paper provides an overview of the collected components of the Kazakh-Russian Sign Language Corpus and the resulting outcomes derived from them. © 2024 ELRA Language Resources Association: CC BY-NC 4.0.

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：