检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Wang, Wentao Shen, Yi Chen, Kaiyang Lu, Kaifan Department of Computer Science University of Southern California LA United States Robotics Department University of Michigan MI United States Department of Electrical and Computer Engineering University of Illinois Urbana-Champaign Champaign United States

Search-based motion planning algorithms have been widely utilized for unmanned aerial vehicles (UAVs). However, deploying these algorithms on real UAVs faces challenges due to limited onboard computational resources. The algorithms struggle to find solutions in high-dimensional search spaces and require considerable time to ensure that the trajectories are dynamically feasible. This paper incorporates the lazy search concept into search-based planning algorithms to address the critical issue of real-time planning for collision-free and dynamically feasible trajectories on UAVs. We demonstrate that the lazy search motion planning algorithm can efficiently find optimal trajectories and significantly improve computational efficiency. © 2024, CC BY.

关键词： Trajectories

来源：评论

学校读者我要写书评

暂无评论

Van der Waals integration inch-scale 2D MoSe_(2) layers on Si for highly-sensitive broadband photodetection and imaging

引用

Nano Research 2023年第8期16卷 11422-11429页

作者： Yupiao Wu Shuo-En Wu Jinjin Hei Longhui Zeng Pei Lin Zhifeng Shi Qingming Chen Xinjian Li Xuechao Yu Di Wu School of Physics and Microelectronics and Key Laboratory of Material PhysicsZhengzhou UniversityZhengzhou 450052China Department of Electrical and Computer Engineering University of California San DiegoLa JollaCA 92093USA School of Microelectronics Science and Technology Sun Yat-Sen UniversityZhuhai 519082China Key Laboratory of Multifunctional Nanomaterials and Smart Systems Suzhou Institute of Nano-Tech and Nano-BionicsChinese Academy of SciencesSuzhou 215123China

As one of the most promising materials for two-dimensional transition metal chalcogenides(2D TMDs),molybdenum diselenide(MoSe_(2))has great potential in photodetectors due to its excellent properties like tunable bandgap,high carrier mobility,and excellent air *** 2D MoSe_(2)-based photodetectors have been reported to exhibit admired performance,the large-area 2D MoSe_(2)layers are difficult to be achieved via conventional synthesis methods,which severely impedes its future ***,we present the controllable growth of large-area 2D MoSe_(2)layers over 3.5-inch with excellent homogeneity by a simple post-selenization ***,a high-quality n-MoSe_(2)/p-Si van der Waals(vdW)heterojunction device is in-situ fabricated by directly growing 2D n-MoSe_(2)layers on the patterned p-Si substrate,which shows a self-driven broadband photoresponse ranging from ultraviolet to mid-wave infrared with an impressive responsivity of 720.5 mA·W^(−1),a high specific detectivity of 10^(13) Jones,and a fast response time to follow nanosecond pulsed optical *** addition,thanks to the inch-level 2D MoSe_(2)layers,a 4×4 integrated heterojunction device array is achieved,which has demonstrated good uniformity and satisfying imaging *** large-area 2D MoSe_(2)layer and its heterojunction device array have great promise for high-performance photodetection and imaging applications in integrated optoelectronic systems.

关键词： molybdenum diselenide large-area synthesis broadband photodetector integrated device array van der Waals(vdW)heterojunction

来源：评论

学校读者我要写书评

暂无评论

Evaluation and Survey of State of the Art Malware Detection and Classification Techniques: Analysis and Recommendation

SSRN

引用

SSRN 2022年

作者： Maniriho, Pascal Mahmood, Abdun Naser Chowdhury, Mohammad Jabed Morshed Department of Computer Science and Information Technology La Trobe University MelbourneVIC Australia

Malware attacks are increasing worldwide and are spreading among different platforms such as desktop and mobile. Malware can potentially damage the compromised system and leak its confidential information. Security breaches caused by malware have led to high demand for designing and building new advanced malware detection techniques as traditional signature-based techniques often fall short to detect a new generation of malware. Fortunately, machine learning and deep learning-based malware detection techniques have been proven to be more effective in detecting malware attacks. This paper presents a survey of existing machine learning-based malware detection techniques and evaluates the performance of state-of-the-art machine learning techniques for malware detection. We evaluate the effects of data scaling/transformation, feature selection, and imbalanced and small datasets. We also present existing public benchmark datasets of malware and benign files, categories of malware detection techniques, and their deployment methods. Moreover, current deep learning-based malware detection techniques are also reviewed, and their performance is evaluated. This work also presents research issues that create serious challenges for researchers and security practitioners. Our experimental results demonstrate that data scaling and feature selection can improve the performance of some of the machine learning and deep learning-based malware detection techniques. © 2022, The Authors. All rights reserved.

关键词： Surveys

来源：评论

学校读者我要写书评

暂无评论

Developers’ Privacy Education: A game framework to stimulate secure coding behaviour

arXiv

引用

arXiv 2022年

作者： Alhazmi, Abdulrahman Hassan Hameed, Mumtaz Abdul Arachchilage, Nalin Asanka Gamagedara The Department of Computer Science and IT La Trobe University Australia Jazan University Saudi Arabia Technovation Consulting & Training PVT The School of Computer Science The University of Auckland New Zealand La Trobe University Australia

Software privacy provides the ability to limit data access to unauthorized parties. Privacy is achieved through different means, such as implementing GDPR into software applications. However, previous research revealed that the lack of poor coding behaviour leads to privacy breaches such as personal data breaching. Therefore, this research proposes a novel game framework as a training intervention enabling developers to implement privacy-preserving software systems. The proposed framework was empirically investigated through a survey study (with some exit questions), which revealed the elements that should be addressed in the game design framework. The developed game framework enhances developers' secure coding behaviour to improve the privacy of the software they develop. © 2022, CC BY.

关键词： Application programs

来源：评论

学校读者我要写书评

暂无评论

Deep Learning Models for Detecting Malware Attacks

arXiv

引用

arXiv 2022年

作者： Maniriho, Pascal Mahmood, Abdun Naser Chowdhury, Mohammad Jabed Morshed Department of Computer Science and Information Technology La Trobe University MelbourneVIC Australia

Malware is one of the most common and severe cyber-attack today. Malware infects millions of devices and can perform several malicious activities including mining sensitive data, encrypting data, crippling system performance, and many more. Hence, malware detection is crucial to protect our computers and mobile devices from malware attacks. Deep learning (DL) is one of the emerging and promising technologies for detecting malware. The recent high production of malware variants against desktop and mobile platforms makes DL algorithms powerful approaches for building scalable and advanced malware detection models as they can handle big datasets. This work explores current deep learning technologies for detecting malware attacks on the Windows, Linux, and Android platforms. Specifically, we present different categories of DL algorithms, network optimizers, and regularization methods. Different loss functions, activation functions, and frameworks for implementing DL models are presented. We also present feature extraction approaches and a review of recent DL-based models for detecting malware attacks on the above platforms. Furthermore, this work presents major research issues on malware detection including future directions to further advance knowledge and research in this field. © 2022, CC BY.

关键词： Android (operating system)

来源：评论

学校读者我要写书评

暂无评论

FastMig: Leveraging FastFreeze to Establish Robust Service Liquidity in Cloud 2.0

FastMig: Leveraging FastFreeze to Establish Robust Service L...

引用

IEEE International Conference on Cloud Computing, CLOUD

作者： Sorawit Manatura Thanawat Chanikaphon Chantana Chantrapornchai Mohsen Amini Salehi Department of Computer Engineering HPCNC Lab Kasetsart University Thailand HPCC Lab School of Computing and Informatics University of Louisiana Lafayette LA USA Computer Science and Engineering Department HPCC Lab University of North Texas TX USA

ISBN: (数字)9798350368536

ISBN: (纸本)9798350368543

Service liquidity across edge-to-cloud or multi-cloud will serve as the cornerstone of the next generation of cloud computing systems (Cloud 2.0). Provided that cloud-based services are predominantly containerized, an efficient and robust live container migration solution is required to accomplish service liquidity. In a nod to this growing requirement, in this research, we leverage FastFreeze, a popular platform for process check-point/restore within a container, and promote it to be a robust solution for end-to-end live migration of containerized services. In particular, we develop a new platform, called FastMig that proactively controls the checkpoint/restore operations of FastFreeze, thereby, allowing for robust live migration of containerized services via standard HTTP interfaces. The proposed platform introduces post-checkpointing and pre-restoration operations to enhance migration robustness. Notably, the pre-restoration operation includes containerized service startup options, enabling warm restoration and reducing the migration downtime. In addition, we develop a method to make FastFreeze robust against failures that commonly happen during the migration and even during the normal operation of a containerized service. Experimental results under real-world settings show that the migration downtime of a containerized service can be reduced by 30X compared to the situation where the original FastFreeze was deployed for the migration. Moreover, we demonstrate that FastMig and warm restoration method together can significantly mitigate the container startup overhead. Importantly, these improvements are achieved without any significant performance reduction and only incurs a small resource usage overhead, compared to the bare (i.e., non-FastFreeze) containerized services.

关键词： Cloud computing Fault tolerance Privacy Fault tolerant systems Machine learning Containers Robustness

来源：评论

学校读者我要写书评

暂无评论

Tuning Zinc-Copper Dual-Ion Electrolytes to Extend the Cycle Life of Zinc Ion Capacitors

Tuning Zinc-Copper Dual-Ion Electrolytes to Extend the Cycle...

引用

International Flexible Electronics Technology Conference (IFETC)

作者： Jinwook Jung Chanho Shin Tse Nga Ng Program in Materials Science and Engineering University of California San Diego La Jolla USA Department of Electrical and Computer Engineering University of California San Diego La Jolla USA

ISBN: (数字)9798331529468

ISBN: (纸本)9798331529475

We investigated the effect of copper ion concentration in zinc-copper dual-ion electrolytes to suppress dendrites and extend the cycle life of zinc ion capacitors. The devices were characterized in terms of changes in microstructure and cycling stability. The nuclei size was decreased in the optimal copper ion concentration to promote lateral deposition and avoid vertical dendrites. The device exhibited stable cycling performance with a capacitance retention of 95% after 10,000 redox cycles, compared to the device with single zinc ion electrolyte which short circuited at around 1,250 redox cycles.

关键词： Performance evaluation Capacitors Redox Ions Electrolytes Dendrites (neurons) Copper Microstructure Zinc Tuning

来源：评论

学校读者我要写书评

暂无评论

Enhancing Recommender Systems with NLP-based Biased Singular Value Decomposition

Enhancing Recommender Systems with NLP-based Biased Singular...

引用

computer Technology and Information science (ISCTIS), International Symposium on

作者： Hong Xu Department of Computer Science and Engineering University of California San Diego La Jolla CA USA

This research introduces a novel Natural language Processing (NLP) based Biased Singular Value Decomposition (SVD) Recommender System that addresses the limitations of existing methods while maintaining high-quality recommendations. By incorporating advanced NLP techniques and Biased SVD, this paper introduces a controlled bias that accounts for both user and item biases, effectively enhancing the performance of the recommender system while maintaining a certain degree of fairness and transparency. In addition, neural network-driven sequential models are incorporated to enhance the recommender system's overall performance. These approaches contribute to the development of efficient, fair, and transparent recommender systems that cater to the diverse needs and preferences of users in the digital era.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Semantic Approach for the classification of Knowledge representation and reasoning analysis

Semantic Approach for the classification of Knowledge repres...

引用

Advances in Computing, Communication Control and Networking (ICAC3N), International Conference on

作者： Karnam Akhil A.Brahmananda Redddy Ragireddy Rahul Reddy Abhinav Borad Department of Computer Science and Engineering VnrVignana Jyothi Institute of Engineering And Technology Hyderabad India Department of Engineering Manufacturing La Trobe University Australia Department of Computer Science and Engineering Malla Reddy Engineering College Hyderabad India

A form of artificial intelligence (AI) that is advanced and involves rules that are applied to data to simulate a person's thought process in a particular area, knowledge engineering can be described as an advanced form of artificial intelligence (AI). Knowledge engineering had evolved from its original form when it focused on transferring and analyzing knowledge from human problem-solvers into computer programs that could do the same. .It is essential to realize that transfer processing has limitations because humans make decisions differently than machines do. Non-linear thinking and analogous reasoning, often not logical, have not been considered in this *** is becoming increasingly common today to use a modeling process for knowledge engineering, which creates a system that can reach the same conclusions as experts without following the same path or acquiring the same information from the same sources. In this paper, we aim to represent Knowledge engineering to transform knowledge into software that makes decisions similar to those made by human experts, such as financial advisors, whose decisions are based on their ***, it is expected that human experts will be replaced by knowledge engineering in decision support software

关键词： Knowledge engineering Computational modeling Semantics Transforms Knowledge representation Software Cognition

来源：评论

学校读者我要写书评

暂无评论

Automated Phytosensing: Ozone Exposure Classification Based on Plant Electrical Signals

Automated Phytosensing: Ozone Exposure Classification Based ...

引用

Computational Intelligence for Energy, Transport and Environmental Sustainability (CIETES), IEEE Symposia on

作者： Till Aust Eduard Buss Felix Mohr Heiko Hamann Department of Computer and Information Science University of Konstanz Konstanz Germany Faculty of Engineering Universidad de La Sabana Chía Colombia.

ISBN: (数字)9798331508258

ISBN: (纸本)9798331508265

In our project WatchPlant, we propose to use a decentralized network of living plants as air-quality sensors by measuring their electrophysiology to infer the environmental state, also called phytosensing. We conducted in-lab experiments exposing ivy (Hedera helix) plants to ozone, an important pollutant to monitor, and measured their electrophysiological response. However, there is no well established automated way of detecting ozone exposure in plants. We propose a generic automatic toolchain to select a high-performance subset of features and highly accurate models for plant electrophysiology. Our approach derives plant- and stimulus-generic features from the electrophysiological signal using the tsfresh library. Based on these features, we automatically select and optimize machine learning models using AutoML. We use forward feature selection to increase model performance. We show that our approach successfully classifies plant ozone exposure with accuracies of up to 94.6% on unseen data. We also show that our approach can be used for other plant species and stimuli. Our toolchain automates the development of monitoring algorithms for plants as pollutant monitors. Our results help implement significant advancements for phytosensing devices contributing to the development of cost-effective, high-density urban air monitoring systems in the future.

关键词： Gases Accuracy Conferences Green products Electrophysiology Feature extraction Libraries Pollution measurement Sensors Monitoring

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：