检索结果-内蒙古大学图书馆

Generic Drone Simulator: Design, Development and User Testing in a Virtual Search and Rescue Mission

IEEE computer Graphics and Applications 2025年 PP卷 PP页

作者： Pappas, Georgios Lappas, Dimitrios Karampelas, Panagiotis Siegel, Joshua E. Templalexis, Ioannis Stavrou, Stavros Krishnan, Sriram Open University of Cyprus Lab of Educational Material and Methodology Latsia Nicosia Cyprus University of the Aegean Learning Technology and Educational Engineering Laboratory Rhodes Greece Hellenic Air Force Academy Department of Informatics & Computers Dekelia Attiki Greece Michigan State University Department of Computer Science and Engineering East LansingMI United States Hellenic Air Force Academy Department of Thermodynamics Propulsion and Power Systems Dekelia Attiki Greece Open University of Cyprus Cybersecurity and Telecommunications Research Lab Latsia Nicosia Cyprus Indian Institute of Technology The Energy Consortium Madras India

This study addresses the need for scenario-specific drone simulators to enhance research, education, pilot training, and performance evaluation across diverse mission contexts. A gamified simulator was developed for the joint master's degree program "Security and Defence" between the Open University of Cyprus (OUC) and the Hellenic Air Force Academy (HAFA), with a focus on Search and Rescue mission training and planning. The simulator balances interface design, physics accuracy, and environmental realism to support specialized professional training and research. A survey-based evaluation involving 57 participants –pilots, engineers, and air traffic controllers –demonstrated the tool's ability to provide realistic experiences for trained pilots and meaningful learning opportunities for novices. Statistical analysis revealed significant correlations between gaming familiarity, task completion times, and participant expertise. © 1981-2012 IEEE.

关键词： Drones

来源：评论

学校读者我要写书评

暂无评论

The Smart Analysis of Performing Scalable Inference for Big Data Analytics

The Smart Analysis of Performing Scalable Inference for Big ...

引用

International Conference on Power Energy, Environment and Intelligent Control (PEEIC)

作者： Vishakha D Bhandarkar Aruna Sri Rongali Mohamed Dawood Shamout Prof. Sachin Pund Gigih Forda Nama Shrishailappa Patil Applied Mathematics and Humanities Yeshwantrao Chavan College of Engineering India Graduate Doctoral Information Technology/Graduate (Information Technology Emphasis/Information Technology Ph.D.) University of The Cumberlands US Department of Management College of Business Administration University of Sharjah Sharjah United Arab Emirates Department of Industrial Engineering Shri Ramdeobaba College of Engineering and Management Nagpur Maharashtra India Department of Informatics Doctoral Program of Environtmental Science University of Lampung Bandar Lampung Computer engineering Vishwakarma Institute of Technology Pune

This paper examines the reproducibility of massive information analytics under particular factors. The paper proposes the “performing Scalable Inference” technique to cope with scalability troubles and to exploit current big statistics platforms for efficient computing and statistics garage of the statistics. In particular, the paper describes how to perform leak-free, parallelizable visible analytics over massive datasets using present extensive records analytics frameworks such as Apache Flink. This method presents an automated manner to execute analytics that preserves reproducibility and the ability to make adjustments without re-running the entire technique. The paper also demonstrates how these analytics may help several real-world use instances, explore affected person cohorts for studies, and develop stratified patient cohorts for hospital therapy. In the end, the paper observes how the proposed method may be exercised within the real world. Actively scalable inference for massive information analytics is pivotal in optimizing decision-making and allocation of assets. Typically, such inferences are made based on information accumulated from numerous sources, databases, unstructured data, and different digital sources. So one can ensure scalability, a complete cloud-primarily based platform has to be hired. This solution will permit the ***, deploying the essential records series and evaluation algorithms are prime here. It could permit the platform to recognize the styles inside the statistics and discover any ability correlations or traits. Additionally, predictive analytics and system mastering strategies may be incorporated to provide insights into the results of the information. In the long run, by leveraging those techniques, the platform can draw efficient inferences and appropriately compare situations in an agile and green way..

关键词：

来源：评论

学校读者我要写书评

暂无评论

Integrated ARM ***-Mali pipeline for high-throughput CNN inference

TechRxiv

引用

TechRxiv 2021年

作者： Aghapour, Ehsan Pathania, Anuj Ananthanarayanan, Gayathri The Informatics Departments University of Amsterdam Netherlands The Department of Computer Science and Engineering Indian Institute of Technology Karnataka Dharwad India

Heterogeneous Multi-Processor System on Chips (HMPSoCs) combine several types of processors on a single chip. State-of-the-art embedded devices are becoming ever more powerful thanks to advancements in the computation power of HMPSoCs that enable them. Consequently, these devices increasingly perform the task of Machine Learning (ML) inferencing at the edge. State-of-the-art HMPSoCs can perform on-chip embedded inference on its CPU and GPU. Multi-component pipelining is the method of choice to provide high-throughput Convolutions Neural Network (CNN) inference on embedded platforms. In this work, we provide details for the first CPU-GPU pipeline design for CNN inference called Pipe-All. Pipe-All uses the ARM-CL library to integrate an ARM *** CPU with an ARM Mali GPU. Pipe-All is the first three-stage CNN inference pipeline design with ARM’s big CPU cluster, Little CPU cluster, and Mali GPU as its stages. Pipe-All provides on average 75.88% improvement in inference throughput (over peak single-component inference) on Amlogic A311D HMPSoC in Khadas Vim 3 embedded platform. We also provide an open-source implementation for Pipe-All under MIT License. © 2021, CC BY.

关键词： System-on-chip

来源：评论

学校读者我要写书评

暂无评论

Kartalol: A New Deep Neural Network Framework Based on Transfer Learning for Iris Segmentation and Localization Task: New Dataset for Iris Segmentation

SSRN

引用

SSRN 2022年

作者： Khiarak, Jalil Nourmohammadi Oskouei, Amin Golzari Nasab, Samaneh Salehi Jaryani, Farhang Moafinejad, Seyed Naeim Pourmohamad, Rana Amini, Yasin Noshad, Morteza Institute of Control and Computation Engineering Warsaw University of Technology Warsaw Poland Department of Computer Engineering Faculty of Electrical and Computer Engineering University of Tabriz Iran School of Engineering Lorestan University Aleshtar Campus Aleshtar Iran Malek-Ashtar University of Technology Department of Physics Shahid Beheshti University Tehran Iran School of Computing Informatics and Decision Systems Engineering Arizona State University AZ United States Faculty of Electrical and Computer Engineering University of Kharazmi Iran Stanford University United States

Iris segmentation and localization in unconstrained environments is challenging due to long distances, illumination variations, limited user cooperation, and moving subjects. Some existing methods in the literature, each of which has somehow mitigated some of the mentioned issues. In this paper, motivated by these weaknesses, we propose a framework that employs a deep neural network-based approach to iris segmentation and localization. The proposed framework is based on a U-Net architecture that has been initialized with a pre-trained MobileNetV2 model. In addition, we have collected 1000 images to study the detectors in iris recognition scenarios better. The provided dataset (KartalOl) is available free for the research community. In the proposed framework, to better generalizability, we fine-tune the MobileNetV2 model on the provided data for NIR-ISL 2021 from the CASIA-Iris-Asia, CASIA-Iris-M1, and CASIA-Iris-Africa and our dataset. Also, data augmentation technics are applied on images. We chose the binarization threshold for the binary masks by iterating over the images in the provided dataset. The proposed framework is trained and tested in CASIA-Iris-Asia, CASIA-Iris-M1, CASIA-Iris-Africa, along the KartalOl dataset. The experimental results highlight that our method surpasses state-of-the-art methods on mobile-based benchmarks. The codes and evaluation results are publicly available at https://***/Jalilnkh/KartalOl-NIR-ISL2021031301. © 2022, The Authors. All rights reserved.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Vulnerability Detection with Graph Simplification and Enhanced Graph Representation Learning

arXiv

引用

arXiv 2023年

作者： Wen, Xin-Cheng Chen, Yupan Gao, Cuiyun Zhang, Hongyu Zhang, Jie M. Liao, Qing School of Computer Science and Technology Harbin Institute of Technology Shenzhen China School of Big Data and Software Engineering Chongqing University China Department of Informatics King’s College London United Kingdom Guangdong Provincial Key Laboratory of Novel Security Intelligence Technologies China Peng Cheng Laboratory China

Prior studies have demonstrated the effectiveness of Deep Learning (DL) in automated software vulnerability detection. Graph Neural Networks (GNNs) have proven effective in learning the graph representations of source code and are commonly adopted by existing DL-based vulnerability detection methods. However, the existing methods are still limited by the fact that GNNs are essentially difficult to handle the connections between long-distance nodes in a code structure graph. Besides, they do not well exploit the multiple types of edges in a code structure graph (such as edges representing data flow and control flow). Consequently, despite achieving state-of-the-art performance, the existing GNN-based methods tend to fail to capture global information (i.e., long-range dependencies among nodes) of code graphs. To mitigate these issues, in this paper, we propose a novel vulnerability detection framework with grAph siMplification and enhanced graph rePresentation LEarning, named AMPLE. AMPLE mainly contains two parts: 1) graph simplification, which aims at reducing the distances between nodes by shrinking the node sizes of code structure graphs;2) enhanced graph representation learning, which involves one edge-aware graph convolutional network module for fusing heterogeneous edge information into node representations and one kernel-scaled representation module for well capturing the relations between distant graph nodes. Experiments on three public benchmark datasets show that AMPLE outperforms the state-of-the-art methods by 0.39%-35.32% and 7.64%-199.81% with respect to the accuracy and F1 score metrics, respectively. The results demonstrate the effectiveness of AMPLE in learning global information of code graphs for vulnerability detection. © 2023, CC BY.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Interfacial magnetic characteristics of nearly compensated gadolinium iron garnet

引用

Physical Review Materials 2024年第4期8卷 044403-044403页

作者： Karthik Srinivasan Alexander J. Grutter Thomas E. Gage P. Quarterman Christy J. Kinane Andrew J. Caruana Guichuan Yu Javier Garcia-Barriocanal Sean Langridge Bethanie J. H. Stadler Department of Electrical and Computer Engineering University of Minnesota 200 Union Street SE Minneapolis Minnesota 55455 USA Department of Electrical and Computer Engineering Boise State University Boise Idaho 83725 USA NIST Center for Neutron Research National Institute of Standards and Technology Gaithersburg Maryland 20878 USA Center for Nanoscale Materials Argonne National Laboratory Lemont Illinois 60439 USA ISIS-Neutron and Muon Source STFC Rutherford Appleton Laboratory Didcot Oxfordshire OX11 0QX United Kingdom Characterization Facility University of Minnesota 100 Union Street SE Minneapolis Minnesota 55455 USA Institute of Informatics University of Minnesota 2231 6th Street SE Minneapolis Minnesota 55455 USA

Reports on spin Hall magnetoresistance, magnonic spin currents from thermal gradients, and spin transfer-torque magnetic random-access memory using compensated ferrimagnets largely discuss bulk magnetization but lack consideration of depth profiles or interfacial characteristics. Here, magnetic and structural characterization of profiles and interfaces was performed for nearly compensated gadolinium iron garnet (GdIG) thin films. X-ray diffraction and reciprocal space maps show that sputter deposited GdIG on Si is polycrystalline with the desired cubic garnet phase, and GdIG on gadolinium gallium garnet (GGG) is epitaxial with <0.06% compressive strain. Temperature-dependent magnetometry confirms the compensation temperatures of GGG/GdIG and Si/GdIG to be 285 and 260 K, respectively, both near room temperature. Interestingly, these measurements suggest the presence of unsaturated rare-earth moments, which result in a characteristic hysteresis between heating and cooling sequences in the magnetization-temperature curves at zero field. Depth-profile measurements from polarized neutron reflectometry (PNR) indicate up to 91% volume fraction in GdIG on Si. At the interface, PNR reveals a region containing magnetized Fe-doped GGG, a low-density GdIG at the GGG/GdIG interface, and a thin magnetically dead layer at the Si/GdIG interface. Cross-sectional transmission electron microscopy and energy dispersive x-ray spectroscopy confirm the assessment of PNR. The magnetic characteristics of interfacial regions are attributed to intermixing of Fe-Ga at the GGG/GdIG interface and the presence of amorphous Fe-Si at the Si/GdIG interface.

关键词： Ferrimagnetism Magnetic insulators Rare-earth magnetic materials Magnetization measurements Neutron reflectometry Scanning transmission electron microscopy Sputtering

来源：评论

学校读者我要写书评

暂无评论

The state-of-the-art review on resource allocation problem using artificial intelligence methods on various computing paradigms

arXiv

引用

arXiv 2022年

作者： Joloudari, Javad Hassannataj Mojrian, Sanaz Saadatfar, Hamid Nodehi, Issa Fazl, Fatemeh Shirkharkolaie, Sahar Khanjani Alizadehsani, Roohallah Dipu Kabir, H.M. Tan, Ru-San Rajendra Acharya, U. Department of Computer Engineering Faculty of Engineering University of Birjand Birjand*** Iran Department of Information Technology Mazandaran University of Science and Technology Babol Iran Department of Computer Engineering Qom University of Technology Qom Iran Department of Electronic Engineering Faculty of Electrical and Computer Engineering University of Birjand Birjand Iran Institute for Intelligent Systems Research and Innovation Deakin University GeelongVIC3216 Australia School of Science and Technology Singapore University of Social Sciences Singapore Ngee Ann Polytechnic Singapore599489 Singapore Dept. of Biomedical Informatics and Medical Engineering Asia University Taichung Taiwan

With the increasing growth of information through smart devices, increasing the quality level of human life requires various computational paradigms presentation including the Internet of Things, fog, and cloud. Between these three paradigms, the cloud computing paradigm as an emerging technology adds cloud layer services to the edge of the network so that resource allocation operations occur close to the end-user to reduce resource processing time and network traffic overhead. Hence, the resource allocation problem for its providers in terms of presenting a suitable platform, by using computational paradigms is considered a challenge. In general, resource allocation approaches are divided into two methods, including auction-based methods (goal, increase profits for service providers-increase user satisfaction and usability) and optimization-based methods (energy, cost, network exploitation, Runtime, reduction of time delay). In this paper, according to the latest scientific achievements, a comprehensive literature study (CLS) on artificial intelligence methods based on resource allocation optimization without considering auction-based methods in various computing environments are provided such as cloud computing, Vehicular Fog Computing, wireless, IoT, vehicular networks, 5G networks, vehicular cloud architecture, machine-to-machine communication (M2M), Train-to-Train(T2T) communication network, Peer-to-Peer (P2P) network. Since deep learning methods based on artificial intelligence are used as the most important methods in resource allocation problems;Therefore, in this paper, resource allocation approaches based on deep learning are also used in the mentioned computational environments such as deep reinforcement learning, Q-learning technique, reinforcement learning, online learning, and also Classical learning methods such as Bayesian learning, Cummins clustering, Markov decision process. © 2022, CC BY-SA.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Vulnerability Detection with Graph Simplification and Enhanced Graph Representation Learning

Vulnerability Detection with Graph Simplification and Enhanc...

引用

International Conference on Software engineering (ICSE)

作者： Xin-Cheng Wen Yupan Chen Cuiyun Gao Hongyu Zhang Jie M. Zhang Qing Liao School of Computer Science and Technology Harbin Institute of Technology Shenzhen China Peng Cheng Laboratory and Guangdong Provincial Key Laboratory Novel Security Intelligence Technologies School of Big Data and Software Engineering Chongqing University China Department of Informatics King's College London UK Peng Cheng Laboratory

Prior studies have demonstrated the effectiveness of Deep Learning (DL) in automated software vulnerability detection. Graph Neural Networks (GNNs) have proven effective in learning the graph representations of source code and are commonly adopted by existing DL-based vulnerability detection methods. However, the existing methods are still limited by the fact that GNNs are essentially difficult to handle the connections between long-distance nodes in a code structure graph. Besides, they do not well exploit the multiple types of edges in a code structure graph (such as edges representing data flow and control flow). Consequently, despite achieving state-of-the-art performance, the existing GNN-based methods tend to fail to capture global information (i.e., long-range dependencies among nodes) of code graphs. To mitigate these issues, in this paper, we propose a novel vulnerability detection framework with grAph siMplification and enhanced graph rePresentation LEarning, named AMPLE. AMPLE mainly contains two parts: 1) graph simplification, which aims at reducing the distances between nodes by shrinking the node sizes of code structure graphs; 2) enhanced graph representation learning, which involves one edge-aware graph convolutional network module for fusing heterogeneous edge information into node representations and one kernel-scaled representation module for well capturing the relations between distant graph nodes. Experiments on three public benchmark datasets show that AMPLE outperforms the state-of-the-art methods by 0.39%-35.32% and 7.64%-199.81% with respect to the accuracy and F1 score metrics, respectively. The results demonstrate the effectiveness of AMPLE in learning global information of code graphs for vulnerability detection.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Development of Educational Game for Indonesian History Lesson Focusing on Indonesia Pre-Literacy Relics 'Prehistoria' for Grade X High School Student

Development of Educational Game for Indonesian History Lesso...

引用

2020 International Conference on computer engineering, Network, and Intelligent Multimedia, CENIM 2020

作者： Nugroho, Supeno Mardi Susiki Rahman, Muhammad Daffa Abiyyu Hariadi, Mochamad Arief, Muhammad Faculty of Intelligent Electrical and Informatics Technology Sepuluh Nopember Institute of Technology Computer Engineering Department Surabaya Indonesia Tokyo University of Technology Media Science Program Graduate School of Bionics Computer and Media Sciences Tokyo Japan

ISBN: (纸本)9781728182834

The development of game technology has opened up new possibilities in learning methods through educational games. However, in Indonesia, the application of this concept is lacking. One lesson that can benefit from educational games is Indonesian History in class X, with a focus on history in the pre-literacy period. This study aims to create a puzzle-Adventure type of digital game that can help educate students about the pre-literacy period, developed with Unity, and uses WebGL as a target device while referring to Indonesia's revised 2013 national curriculum. The result of this research is the creation of a digital game that can be played on average of 254.36 seconds, with potential for educational use. A survey result shows that many of the ancient objects and some of the ages are well-recognized. However, the survey also shows many of the gameplay aspects, such as UI, gameplay features, and adventure elements, need improvements. © 2020 IEEE.

关键词： Surveys

来源：评论

学校读者我要写书评

暂无评论

Work Engagement Recognition in Smart Office

引用

Procedia computer science 2022年 200卷 451-460页

作者： Congcong Ma Carman Ka Man Lee Juan Du Qimeng Li Raffaele Gravina Department of Industrial and Systems Engineering The Hong Kong Polytechnic University Hong Kong Special Administrative Region. School of Computer and Software Nanyang Institute of Technology Nanyang 473004 China. Department of Informatics Modeling Electronics and Systems University of Calabria Rende 87036 Italy.

The COVID-19 pandemic has forced a sudden change of traditional office works to smart working models, which however force many workers staying at home with a significant increase of sedentary lifestyle. Metabolic disorders, mental illnesses, and musculoskeletal injuries are also caused by the physical inactivity and chronic stress at work, threatening office workers' physical and physiological health. In the modern vision of smart workplaces, cyber-physical systems play a central role to augment objects, environments, and workers with integrated sensing, data processing, and communication capabilities. In this context, a work engagement system is proposed to monitor psycho-physical comfort and provide health suggestion to the office workers. Recognizing their activity, such as sitting postures and facial expressions, could help assessing the level of work engagement. In particular, head and body posture could reflects their state of engagement, boredom or neutral condition. In this paper we proposed a method to recognize such activities using an infrared sensor array by analyzing the sitting postures. The proposed approach can unobstructively sense their activities in a privacy-preserving way. To evaluate the performance of the system, a working scenario has been set up, and their activities were annotated by reviewing the video of the subjects. We carried out an experimental analysis and compared Decision Tree and k-NN classifiers, both of them showed high recognition rate for the eight postures. As to the work engagement assessment, we analyzed the sitting postures to give the users suggestions to take a break when the postures such as lean left/right with arm support, lean left/right without arm support happens very often.

关键词： Infrared Sensor Sitting Posture Recognition Smart Office Work Engagement

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：