检索结果-内蒙古大学图书馆

15th International Conference on Information, Intelligence, Systems and Applications, IISA 2024

作者： Meimetis, Dimitrios Daramouskas, Ioannis Lappas, Vaios Perikos, Isidoros Kapoulas, Vaggelis Paraskevas, Michael Nkua Department of Aerospace Science & Technology Athens Greece Computer Technology Institute and Press 'Diophantus' Patras Greece UoP Applied Mechanics Lab Patras Greece UoP Computer Engineering and Informatics Department Patras Greece Computer Technology Institute and Press 'Diophantus' University of Peloponnese Electrical and Computer Engineering Dept. Patras Greece

ISBN: (纸本)9798350368833

Unmanned aerial vehicles (UAVs) have garnered significant attention from the research community during the last decade, due to their diverse capabilities and potential applications. One of the most critical functions that drones must execute efficiently is navigation in real-world environments. This paper presents a decentralized approach for enabling unmanned aerial vehicles (UAVs) to navigate safely in unknown environments and avoid obstacles. Leveraging the Optimal Reciprocal Collision Avoidance (ORCA) algorithm, implemented in the Robot Operating System (ROS), our method facilitates conflict detection and resolution in 2D environments. Through simulations using ROS, Gazebo, and Iris drones, we validate the effectiveness of our approach in scenarios with initial trajectory conflicts. Our work addresses the pressing need for UAVs to autonomously plan and execute safe flights, laying the groundwork for enhanced UAV capabilities in various real-world applications. The simulation results demonstrate the efficiency and robustness of our approach. © 2024 IEEE.

关键词： Drones

来源：评论

学校读者我要写书评

暂无评论

Exact Solution of the Full RMSA Problem in Elastic Optical Networks

IEEE Networking Letters

引用

IEEE Networking Letters 2024年第1期6卷 55-59页

作者： David, Fabio Rezende, Jose F. De Barbosa, Valmir C. Federal University of Rio de Janeiro Informatics and Computer Science Department Rio de Janeiro21941-914 Brazil Federal University of Rio de Janeiro Systems Engineering and Computer Science Program Centro de Tecnologia Rio de Janeiro21941-914 Brazil

Exact solutions of the Routing, Modulation, and Spectrum Allocation (RMSA) problem in Elastic Optical Networks (EONs), so that the number of admitted demands is maximized while those of regenerators and frequency slots used are minimized, require a complex ILP formulation taking into account frequency-slot continuity and contiguity. We introduce the first such formulation, ending a hiatus of some years since the last ILP formulation for a much simpler RMSA variation was introduced. By exploiting a number of problem and solver specificities, we use the NSFNET topology to illustrate the practicality and importance of obtaining exact solutions. © 2019 IEEE.

关键词： Topology

来源：评论

学校读者我要写书评

暂无评论

Drone-Based Public Surveillance Using 3D Point Clouds and Neuro-Fuzzy Classifier

引用

computers, Materials & Continua 2025年第3期82卷 4759-4776页

作者： Yawar Abbas Aisha Ahmed Alarfaj Ebtisam Abdullah Alabdulqader Asaad Algarni Ahmad Jalal Hui Liu Faculty of Computing and AI Air UniversityIslamabad44000Pakistan Department of Information Systems College of Computer and Information SciencesPrincess Nourah bint Abdulrahman UniversityRiyadh11671Saudi Arabia Department of Information Technology College of Computer and Information SciencesKing Saud UniversityRiyadh12372Saudi Arabia Department of Computer Sciences Faculty of Computing and Information TechnologyNorthern Border UniversityRafha91911Saudi Arabia Department of Computer Science and Engineering College of InformaticsKorea UniversitySeoul02841Republic of Korea Cognitive Systems Lab University of BremenBremen28359Germany

Human Activity Recognition(HAR)in drone-captured videos has become popular because of the interest in various fields such as video surveillance,sports analysis,and human-robot ***,recognizing actions from such videos poses the following challenges:variations of human motion,the complexity of backdrops,motion blurs,occlusions,and restricted camera *** research presents a human activity recognition system to address these challenges by working with drones’red-green-blue(RGB)*** first step in the proposed system involves partitioning videos into frames and then using bilateral filtering to improve the quality of object foregrounds while reducing background interference before converting from RGB to grayscale *** YOLO(You Only Look Once)algorithm detects and extracts humans from each frame,obtaining their skeletons for further *** joint angles,displacement and velocity,histogram of oriented gradients(HOG),3D points,and geodesic Distance are *** features are optimized using Quadratic Discriminant Analysis(QDA)and utilized in a Neuro-Fuzzy Classifier(NFC)for activity ***-world evaluations on the Drone-Action,Unmanned Aerial Vehicle(UAV)-Gesture,and Okutama-Action datasets substantiate the proposed system’s superiority in accuracy rates over existing *** particular,the system obtains recognition rates of 93%for drone action,97%for UAV gestures,and 81%for Okutama-action,demonstrating the system’s reliability and ability to learn human activity from drone videos.

关键词： Activity recognition geodesic distance pattern recognition neuro fuzzy classifier

来源：评论

学校读者我要写书评

暂无评论

Apple Scab Detection Using Transfer Learning and Deep Convolutional Network 7th

Apple Scab Detection Using Transfer Learning and Deep Convol...

引用

7th International Conference on Soft Computing: Theories and Applications, SoCTA 2023

作者： Singh, Anupam Jain, Arjav Batra, Aryan Department of Computer Science and Engineering Graphic Era Hill University Uttarakhand Dehradun India Informatics Cluster School of Computer Science University of Petroleum & Energy Studies Uttarakhand Dehradun248007 India

ISBN: (纸本)9789819720309

Every year, diseases and pests inflict enormous economic losses on the apple industry. One of the significant challenges faced by the farmers is the identification of the various diseases, as the signs and symptoms of several illnesses could be very similar and be present simultaneously. Through this proposed work, we make an effort to offer accurate and timely detection of one such apple disease, i.e., apple scab, a fungal disease. The main reason for choosing apple scab and apple leaves scab detection as our work is due to the lack of research on the topic, and we wanted to take this opportunity to do something meaningful and help the agriculture industry in India. The first part of the work was data preprocessing and labeling. The datasets containing photographs of patch-affected apples and leaves of an apple tree are collected;however, there are hardly any public datasets that contain enough images for us to use and train our models with because the acquisition of these images is extremely time-consuming and has a component of probability;therefore, we decided that transfer learning (TF) would be a suitable training approach. Training deep neural networks from scratch on a small dataset can take a long time and may not converge to a good solution due to overfitting. Transfer learning allowed us to start with a pretrained model and fine-tune it on your specific task. This significantly reduced the training time and resource requirements. The convolutional neural network (CNN) on the collected dataset is the model used to categorize apples. End-to-end learning algorithms known as CNN automatically extract characteristics from raw photographs and learn complex features from them. To avoid our model overfitting, we would use data augmentation techniques like rotation, translation, and scaling. An experimental result demonstrates that using the proposed structure of CNN and transfer learning, the results are comparatively better than the pretrained deep learning mode

关键词： Losses

来源：评论

学校读者我要写书评

暂无评论

An Evaluation of the Dual Vectors Based Solutions for Robot-World/Hand-Eye Calibration 1

引用

25th International Symposium on Measurement and Control in Robotics, ISMCR 2023

作者： Ganciu, Aura Burlacu, Adrian Department of Automatic Control and Applied Informatics Faculty of Automatic Control and Computer Engineering "Gheorghe Asachi" Technical University of Iași Iași Romania

ISBN: (数字)9783031510854

ISBN: (纸本)9783031510847

The hand-eye calibration problem represents a major challenge in robotics, arising from the widespread usage of robotic systems along with robot-mounted sensors. Briefly, consisting of estimating the position and orientation of a visual sensor (usually a camera attached to the robot’s end-effector) with respect to the robot itself, calibration is critical in tracking rigid bodies—a common task within mixed reality applications. Hand-eye calibration implies solving the problem formulated as AX = XB or AX = YB equations. The solution lies in computing the unknown homogeneous transformation matrices X and Y, given the A and B parameterizations of rigid body motions. We present the dual vectors based approaches for AX = XB and AX = YB calibration problems, making use of the isomorphism between the special Euclidean group and the orthogonal dual tensor group. Comparisons with state-of-the-art algorithms are used to assess our obtained results. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.

关键词： Mixed reality

来源：评论

学校读者我要写书评

暂无评论

Gestures detection and device control in AAL environments using machine learning and BLEs 12

Gestures detection and device control in AAL environments us...

引用

12th Mediterranean Conference on Embedded Computing, MECO 2023

作者： Spournias, Alexandros Faliagka, Evanthia Skandamis, Theodoros Antonopoulos, Christos Voros, Nikolaos S. Keramidas, Georgios University of the Peloponnese Electrical & Computer Engineering Department Patra Greece School of Informatics Aristotle University of Thessaloniki Thessaloniki Greece

ISBN: (纸本)9798350322910

This paper presents a system for detecting gestures and controlling devices in Ambient Assisted Living (AAL) environments using machine learning and Bluetooth Low Energy (BLE) technology. The system consists of two main components: a device equipped with a set of sensors to detect hand gestures via IMU sensor and a BLE-enabled hub that receives the gesture data and controls the lighting of the house. The hub uses machine learning algorithms to recognize hand gestures and transmit the corresponding commands to the devices. The hub, in turn, uses wifi to communicate with the devices and execute the appropriate actions based on the received commands. The proposed system's performance evaluation was carried out through a series of experiments in a AAL environment. The results demonstrate that the system is capable of accurately detecting hand gestures and controlling various devices such as lights, where the model's performance yields successful predictions with an accuracy rate of 90%. The proposed system provides a user-friendly and intuitive way for elderly or people with disabilities to control their environment without the need for complex interfaces or physical buttons. Furthermore, the system can be easily extended to support more gestures and devices, making it a flexible and scalable solution for AAL environments. © 2023 IEEE.

关键词： Gesture recognition

来源：评论

学校读者我要写书评

暂无评论

User Interface Rendering Time in Android Applications: Revealing the Effects of Design Patterns 23

User Interface Rendering Time in Android Applications: Revea...

引用

8th International Conference on Sustainable Information engineering and Technology, SIET 2023

作者： Paramadani, Rizky Bagus Akbar, Muhammad Aminul Pinandito, Aryo Informatics Engineering Departement Faculty of Computer Science Universitas Brawijaya Malang Indonesia Information System Department Universitas Brawijaya Faculty of Computer Science Indonesia

ISBN: (纸本)9798400708503

The Google Play platform boasts a total of 2,597,819 applications. A pivotal gauge of an application's success rests on its practical utility in daily life, coupled with its demonstrated strong performance metrics. There are several performance metrics to evaluate the performance of an application, such as RAM usage, CPU utilization, and their impact on battery life. Additionally, it is crucial to consider the User Interface (UI) factor, which serves as the primary connection between users and applications. Beyond its role as a bridge between users and applications, the UI can also significantly affect the performance of an application, as rendering a UI often takes a considerable amount of time. Various approaches can be employed to enhance the rendering time of a UI, one of which involves the use of design patterns like Model-View-Controller (MVC) and Model-View-ViewModel (MVVM), which effectively separate the business logic from the UI layer. This research study compares the performance of these two design patterns in the context of UI rendering time. The findings of this study confirm that MVVM outperforms MVC significantly in rendering UI components more rapidly. This superiority is attributed to MVVM's inherent ability to isolate business logic, ultimately reducing rendering delays. Furthermore, MVVM's prominent data binding feature further strengthens its efficiency in terms of UI rendering time. © 2023 ACM.

关键词： User interfaces

来源：评论

学校读者我要写书评

暂无评论

Supervised Machine Learning Algorithms for the Analysis of Ship Engine Data 16th

Supervised Machine Learning Algorithms for the Analysis of S...

引用

16th EAI International Conference on Wireless Internet, WiCON 2023

作者： Dimitriou, Theodoros Skondras, Emmanouil Hitiris, Christos Gkola, Cleopatra Papapanagiotou, Ioannis S. Vergados, Dimitrios J. Papapanagiotou, Stavros I. Koumantakis, Stratos Michalas, Angelos Vergados, Dimitrios D. Department of Informatics University of Piraeus Piraeus Greece Department of Electrical and Computer Engineering University of Western Macedonia Kozani Greece Department of Informatics University of Western Macedonia Kastoria Greece Internet Business Hellas Athens Greece MAS S.A. Athens Greece

ISBN: (纸本)9783031580529

Supervised Machine Learning (ML) algorithms are used for making predictions or decisions based on labeled data. In this paper, an overview about existing supervised ML algorithms is performed. In particular, the algorithms that are studied comprehend the Linear Regression (LR), the Ridge Regression (RR), the Decision Tree (DT), as well as Ensemble algorithms. Subsequently, a comparative analysis of the algorithms is performed using a dataset containing data about ship engines. Effective management of ship engines is important for their robust operation, which can then bring significant economic and environmental benefits. Inferences about the condition of engines and predictions about their performance could prove crucial for specifying optimal cruise parameters, early fault detection and timely service planning. The analysis demonstrates the strength and the weaknesses of each algorithm in terms of predicting decay factors of the ship engine by taking into consideration the data included to the aforementioned dataset. © ICST Institute for computer Sciences, Social informatics and Telecommunications engineering 2024.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Comparing the Effectiveness of Machine Learning and Deep Learning Techniques for Feature Envy Detection in Software Systems 1

Comparing the Effectiveness of Machine Learning and Deep Lea...

引用

1st International Conference of Intelligent Methods, Systems and Applications, IMSA 2023

作者： Menshawy, Rana S. Yousef, Ahmed H. Salem, Ashraf Faculty of Engineering Computer and System Department Ain Shams University Cairo Egypt Egypt University of Informatics Cairo Egypt

ISBN: (纸本)9798350335569

Code smells are common in poorly designed software that can hinder code maintainability. Automatic detection of design flaws assists developers in identifying code smells in theirsoftware programs to avoid low-quality delivery. However, the interpretation of code smells is subjective, and existing machine learning-based detection tools are limited in their ability to capture complex semantic relationships in textual code. To address this limitation, the paper proposes a detection system that exploits machine learning and deep learning techniques and compares their effectiveness in identifying the feature envy code smell. The study applies six deep learning techniques based on code semantics features extracted from abstract syntax trees, and eleven machine learning techniques based on code structural features. The results show that both approaches are effective in detecting code smells, with Random Forest achieving exceptional performance among the machine learning classifiers. © 2023 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

A Comprehensive Framework for Cold Start Problem in Hybrid Recommendation Systems Extending the Efficient Multi-Mode Approach 27

A Comprehensive Framework for Cold Start Problem in Hybrid R...

引用

27th International computer Science and engineering Conference, ICSEC 2023

作者： Badriyah, Tessy Ramadhan, Yunaz Gilang Syarif, Iwan Informatics and Computer Engineering Department Kampus PENS JL. Arief Rahman Hakim Sukolilo Surabaya60111 Indonesia

ISBN: (纸本)9798350342109

E-Commerce is a prominent application of information technology in business, offering convenience in transactions. However, as more products and users join the platform, the complexity of E-Commerce systems increases. This necessitates the implementation of a recommendation system to enhance the user experience and address individual preferences. E-Commerce platforms often face the challenge of the cold start problem, where new products are introduced to the platform or when there is limited information available about new users. In such cases, traditional recommendation systems struggle to provide accurate recommendations due to the lack of historical data or user preferences. In this research, a comprehensive framework for an efficient multi-mode Hybrid Recommendation System is proposed, focusing on addressing the cold start problem. The system leverages user behavior tracking, specifically search history and product visit history, to capture user preferences effectively. Through experimental evaluation, the system demonstrates its adaptability to different dataset conditions, achieving a high precision rate of 90%. This research addresses the challenges of data sparsity and the cold start problem in recommendation systems, particularly in the E-Commerce context. The flexibility of the recommendation system ensures optimal recommendations in various scenarios, with potential applications beyond E-Commerce. © 2023 IEEE.

关键词： Recommender systems

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：