检索结果-内蒙古大学图书馆

9th NAFOSTED Conference on Information and computer science, NICS 2022

作者： Huu, Phat Nguyen Anh, Bang Nguyen Nam, Vu Tran Ngoc Hoang, Tran Manh Nguyen, Tien Dzung Minh, Quang Tran School of Electrical and Electronic Engineering Hanoi University of Science and Technology Hanoi Viet Nam Specialized Math Class HUS High School for Gifted Students Hanoi Viet Nam Ho Chi Minh City University of Technology Faculty of Computer Science and Engineering Department of Information Systems Hochiminh Viet Nam Vietnam National University HoChiMinh City Hochiminh Viet Nam

ISBN: (纸本)9781665454223

Today, strong development of socio-economic has promoted participation in traffic. As a result, traffic management is becoming more and more difficult. To effectively solve the problem, artificial intelligence (AI) applications are applied for the improvement of urban traffic management and administration. Therefore, we propose an intelligent algorithm for monitoring and detecting vehicles. We use data collected from cameras and apply deep learning technology to track objects in the paper. The proposed algorithm uses YOLOv4 combined with DeepSORT for tracking and calculating the speed of detected vehicles. Results show that the proposed algorithm improves accuracy up to 95% which is suitable to apply for real applications. © 2022 IEEE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Botnet Attack Intrusion Detection In IoT Enabled Automated Guided Vehicles

Botnet Attack Intrusion Detection In IoT Enabled Automated G...

引用

IEEE International Conference on Big Data

作者： Sumaiya Shaikh Ch. Rupa Gautam Srivastava Thippa Reddy Gadekallu Department of CSE Lords Institute of Engineering and Technology Hyderabad India Department of CSE VR Siddhartha Engineering College Vijayawada India Department of Math and Computer Science Brandon University Canada School of Information Technology and Engineering Vellore Institute of Technology India Department of Electrical and Computer Engineering Lebanese American University Byblos Lebanon

ISBN: (纸本)9781665480468

The Internet of Things (IoT), with the ease of access of Automated Vehicles, is the most reliable technology in the 21 st century making every possible thing within seconds. The people in this era are blessed with all the new technology, and new gadgets, due to which many things which used to take longer are done within nanoseconds. IoT combines computing devices, mechanical devices, digital machines, objects, and people which possess the ability to transfer data over the network with Unique identifiers (UIDs) without human intervention. Such IoT-enabled Automated Guided Vehicles (AGV) are more reliable on networks for every action. Deep learning and machine learning techniques are pivotal for the successful implementation of IoT-based applications including AGVs. A botnet refers to the attacks which come from robot Network attacks. Recently, many organizations have been compromised using this attack. Most affected devices are connected to IoT as it uses automatically generated data. The ideology of this study is to propose an intrusion prediction system which can predict botnet attacks in AGVs. In this study, N – Balo dataset is used for classification, clustering and prediction. The technique implemented in this paper may provide some roots to develop the most reliable and highly secured AGV network.

关键词： Deep learning Remotely guided vehicles Botnet Intrusion detection Organizations Big Data Reliability

来源：评论

学校读者我要写书评

暂无评论

MIND-WANDERING DETECTION MODEL WITH ELECTROENCEPHALOGRAM 18

MIND-WANDERING DETECTION MODEL WITH ELECTROENCEPHALOGRAM

引用

18th International Conference on Cognition and Exploratory Learning in Digital Age, CELDA 2021

作者： Rungsilp, Chutimon Piromsopa, Krerk Viriyopase, Atthaphon U-Yen, Kongpop Department of Computer Engineering Faculty of Engineering Chulalongkorn University Bangkok Thailand Research Group on Applied Digital Technology in Medicine Chulalongkorn University Bangkok Thailand Future Innovation Science and Technology Chulalongkorn University Bangkok Thailand

ISBN: (纸本)9789898704337

The study of mind-wandering is popular since it is linked to the emotional problems and working/learning performance. In terms of education, it impacts comprehension during learning which affects academic success. Therefore, we sought to develop a machine learning model for an embedded portable device that can categorize mind-wandering state to assist people in keeping track of their minds. We utilize a low-channel EEG to record the brain state and to build the predictive model because of its practicality and user-friendly. Most machine learning experiments in mind-wandering using EEG exhibit good individual-level performance. For the group-level technique, only a few research has developed a model. As a result, the goal of this research is to achieve a high-accuracy group-level model. Thus, Leave One Participant Out Cross Validation (LOPOCV) was used to assess the model correctness. This study shows that using a baseline normalization technique assists feature extraction and improves performance. The model was built using a support vector machine (SVM), and the best model achieved an accuracy value of 75.6 percent. © 2021 Virtual Simulation Innovation Workshop, SIW 2021. All rights reserved.

关键词： Electroencephalography

来源：评论

学校读者我要写书评

暂无评论

The Space Digital Dome: Autonomous Defense of Space Vehicles from Radio Frequency Interference

The Space Digital Dome: Autonomous Defense of Space Vehicles...

引用

2022 IEEE Aerospace Conference, AERO 2022

作者： Falco, Gregory Gordon, Nathaniel G. Byerly, Adam Grotto, Andrew Siegel, Josh Zanlongo, Sebastian Institute for Assured Autonomy Johns Hopkins University Department of Civil & Systems Engineering BaltimoreMD United States Applied Physics Laboratory Johns Hopkins University LaurelMD United States Cyber Policy Center Stanford University StanfordCA United States Michigan State University Department of Computer Science East LansingMI United States

ISBN: (数字)9781665437608

ISBN: (纸本)9781665437608

While awareness of active threats is critical to space vehicles, action is required to avoid harm. Physical hazard avoidance requires orbital manipulation using propulsion, whereas options for avoiding or nullifying radio frequency interference (RFI) are less straightforward. Because these actions need to occur on the space vehicle in real-time despite limited computing capacity and power on the edge, actions need to be reliably assessed and planned with readily available resources. The space vehicle will need to make fully or partially autonomous decisions to defend its communication channel and ensure mission resilience. This paper proposes an architecture to facilitate the autonomous defense of space vehicles from radio frequency attacks. Further, the paper aims to promote the broader discussion of mechanisms to defend space vehicles from cyber, kinetic, electromagnetic and other attacks. © 2022 IEEE.

关键词： Radio waves

来源：评论

学校读者我要写书评

暂无评论

A Classifier to Detect Stream Applications Based on Network Traffic Statistical Metrics

A Classifier to Detect Stream Applications Based on Network ...

引用

Information Technology (ACIT)

作者： Omar Darwish Sarah Herzallah Majdi Maabreh Shouroq Al-Eidi Mahmoud Al-Maani Yahya Tashtoush Information Security and Applied Computing Eastern Michigan University Ypsilanti Michigan Electrical and Computer Engineering Eastern Michigan University Ypsilanti Michigan Department of Information Technology The Hashemite University Zarqa Jordan Computer Science Department Tafila Technical University Tafila Jordan Department of Computer Science Jordan University of Science and Technology Irbid Jordan

ISBN: (数字)9798350320244

ISBN: (纸本)9798350320251

One of the most crucial considerations, when considering security vulnerabilities, is network traffic. There is still potential for more research on the inter-arrival time side, even though some studies concentrate on network traffic from the perspective of the packet fields such as packet length and packet number. Inter-arrival timings are crucial to investigate because there are numerous attacks, such as Covert Timing Channels attacks, that heavily rely on them. In this article, we conduct a statistical analysis of the TCP inter-arrival times of two major key streaming programs (Zoom and Skype), which are frequently used, particularly during and following the COVID-19 pandemic. Using two internet-connected devices and the statistical measures of TCP, a dataset of 18,371 instances is created for this use. Five machine learning algorithms are evaluated on balanced and imbalanced forms of the dataset. The results revealed that the traffic of Zoom and Skype calls can be identified by machine learning algorithms with an accuracy of up to 99% by random forest.

关键词： Measurement COVID-19 Machine learning algorithms Statistical analysis Pandemics Telecommunication traffic Timing

来源：评论

学校读者我要写书评

暂无评论

Glioma/Glioblastoma Detection in Brain MRI using Pre-trained Deep-Learning Scheme 3

Glioma/Glioblastoma Detection in Brain MRI using Pre-trained...

引用

3rd International Conference on Intelligent Computing, Instrumentation and Control Technologies, ICICICT 2022

作者： Rajinikanth, Venkatesan Kadry, Seifedine Damasevicius, Robertas Sujitha, R. Angel Balaji, Gangadharam Mohammed, Mazin Abed Noroff University College Faculty of Applied Computing and Technology Kristiansand94612 Norway Vytautas Magnus University Department of Applied Informatics Kaunas44404 Lithuania St. Joseph's College of Engineering Department of Electronics and Instrumentation Engineering Omr Chennai600119 India M/S Tata Consultancy Services Limited Tcsl Siruseri Sez Unit Sipcot I.T. Park TN Chennai603103 India University of Anbar College of Computer Science and Information Technology Ramadi31001 Iraq

ISBN: (数字)9781665410052

ISBN: (纸本)9781665410052

Convolutional Neural Network (CNN) supported medicinal image examination is extensively accepted due to its reputation and improved accuracy. The investigational outcome obtained with DLS along with a chosen classifier helps to achieve better detection results than the traditional and machine-learning methods. The proposed research examines the performance of pre-trained VGG16 and VGG19 schemes in detecting the brain tumour (Glioma/Glioblastoma) grade using different pooling methods. The classification is performed using SoftMax with five-fold cross-validation, and the products are compared and presented. The brain tumour images considered in this study are collected from The Cancer Imaging Archive (TCIA) dataset. This work considered 2000 images (1000 Glioma and 1000 Glioblastoma) of axial-plane with dimension of 224×224×3 pixels for the assessment, and the attained results are compared. The experimental outcome achieved with Python® confirms that the VGG16 with average-pooling provides a better classification accuracy (>99%) with Decision Tree (DT) compared with other methods considered. © 2022 IEEE.

关键词： Python

来源：评论

学校读者我要写书评

暂无评论

HomOpt: A Homotopy-Based Hyperparameter Optimization Method

arXiv

引用

arXiv 2023年

作者： Abraham, Sophia J. Maduranga, Kehelwala D.G. Kinnison, Jeffery Carmichael, Zachariah Hauenstein, Jonathan D. Scheirer, Walter J. Department of Computer Science and Engineering University of Notre Dame Notre DameIN46556 United States Department of Mathematics Tennessee Tech University CookevilleTN38505 United States Department of Applied and Computational Mathematics and Statistics University of Notre Dame Notre DameIN46556 United States

Machine learning has achieved remarkable success over the past couple of decades, often attributed to a combination of algorithmic innovations and the availability of high-quality data available at scale. However, a third critical component is the fine-tuning of hyperparameters, which plays a pivotal role in achieving optimal model performance. Despite its significance, hyperparameter optimization (HPO) remains a challenging task for several reasons. Many HPO techniques rely on naive search methods or assume that the loss function is smooth and continuous, which may not always be the case. Traditional methods, like grid search and Bayesian optimization, often struggle to quickly adapt and efficiently search the loss landscape. Grid search is computationally expensive, while Bayesian optimization can be slow to prime. Since the search space for HPO is frequently high-dimensional and non-convex, it is often challenging to efficiently find a global minimum. Moreover, optimal hyperparameters can be sensitive to the specific dataset or task, further complicating the search process. To address these issues, we propose a new hyperparameter optimization method, HomOpt, using a data-driven approach based on a generalized additive model (GAM) surrogate combined with homotopy optimization. This strategy augments established optimization methodologies to boost the performance and effectiveness of any given method with faster convergence to the optimum on continuous, discrete, and categorical domain spaces. We compare the effectiveness of HomOpt applied to multiple optimization techniques (e.g., Random Search, TPE, Bayes, and SMAC) showing improved objective performance on many standardized machine learning benchmarks and challenging open-set recognition tasks. © 2023, CC BY.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

High-power quantum walk frequency combs

arXiv

引用

arXiv 2025年

作者： Letsou, Theodore P. Fuchsberger, Johannes Opačak, Nikola Kazakov, Dmitry Schwarz, Benedikt Capasso, Federico Harvard John A. Paulson School of Engineering and Applied Sciences Harvard University CambridgeMA02138 United States Department of Electrical Engineering and Computer Science Massachusetts Institute of Technology CambridgeMA02142 United States Institute of Solid State Electronics TU Wien Vienna1040 Austria

High-power, broadband frequency combs generated by semiconductor lasers have profound implications for on-chip spectroscopy. Here, we present a dry-etched racetrack quantum cascade laser that uses resonant radio-frequency injection to produce a unidirectional "quantum walk" frequency comb at mid-infrared wavelengths. Efficient light outcoupling from the racetrack resonator provides more than 100 mW of continuous-wave output power at room temperature, with beam quality on par with that of Fabry–Perot lasers. Experimental waveform reconstruction confirms that the combs are frequency-modulated, rather than amplitude-modulated (as in active mode-locking). We show excellent agreement between the experimental waveforms and numerical simulations, which are based on a reduced Maxwell–Bloch model of the laser and include fast gain dynamics, finite group velocity dispersion, and large Kerr nonlinearity. Furthermore, our optimized device architecture — featuring thick Si3N4 passivation and reduced parasitic capacitance — enables modulation bandwidths exceeding 10 GHz. Combined with high output powers and the potential for monolithic integration of multiple ring lasers and waveguide couplers, these advances pave the way to fully integrated dual-comb spectrometers. © 2025, CC BY.

关键词： Ring lasers

来源：评论

学校读者我要写书评

暂无评论

A Comparative Study of Deep Learning Robustness for Sensor-based Human Activity Recognition

A Comparative Study of Deep Learning Robustness for Sensor-b...

引用

International Conference on Telecommunications and Signal Processing (TSP)

作者： Sakorn Mekruksavanich Anuchit Jitpattanakul Department of Computer Engineering School of Information and Communication Technology University of Phayao Phayao Thailand Department of Mathematics Faculty of Applied Science Intelligent and Nonlinear Dynamic Innovations Research Center King Mongkut’s University of Technology North Bangkok Bangkok Thailand

Recognition of human activities has become a highly significant area of research in the current era of the Internet of Things and A.I. technologies. Human activity recognition (HAR) plays a crucial role in monitoring and analyzing human behaviors using various types of sensors. Such sensor-based HAR systems are being used in various industry domains, including healthcare, professional sports, and worker assessment in intelligent factories. The integration of micro electronics mechanical systems sensor technology in smart wearable devices has significantly improved the capabilities of HAR using machine learning and deep learning techniques. However, processing longtime dependent sequence samples with noisy data is still a significant challenge, affecting the classification time and accuracy. This study aimed to analyze noise-tolerant deep learning models for recognizing physical activities from noisy smartphone data. The study analyzed the recognition performances of the five most popular deep learning networks for HAR under different levels of Gaussian noise. The results indicated that the BiGRU network demonstrated outstanding robustness to Gaussian noise of different levels.

关键词：

来源：评论

学校读者我要写书评

暂无评论

AlgoXSSF: Detection and Analysis of Cross-Site Request Forgery (XSRF) and Cross-Site Scripting (XSS) Attacks via Machine Learning Algorithms

AlgoXSSF: Detection and Analysis of Cross-Site Request Forge...

引用

International Symposium on Digital Forensic and Security (ISDFS)

作者： Naresh Kshetri Dilip Kumar James Hutson Navneet Kaur Omar Faruq Osama School of Business & Technology Emporia State University Emporia KS USA Laboratory of Applied Cryptology and Security (LACS) Indian Institute of Technology Mandi India Department of Art History & Culture Lindenwood University Saint Charles Missouri Department of Computer Science University of Missouri St. Louis Missouri USA Department of Systems Science and Industrial Engineering Binghamton University SUNY Binghamton NY USA

ISBN: (数字)9798350330366

ISBN: (纸本)9798350330373

The global rise in online users and devices has led to a corresponding surge in cybercrimes and attacks, demanding advanced technology and algorithms like Artificial Intelligence (AI), Deep Learning, and Machine Learning to bolster web security. The unprecedented increase rate of cybercrime and website attacks urged for new technology consideration to protect data and information online. There have been recent and continuous cyberattacks on websites, web domains with ongoing data breaches including - GitHub account hack, data leaks on Twitter, malware in WordPress plugins, vulnerability in Tomcat server to name just a few. Extensive research has been conducted to detect and analyze prevalent cyber threats like cross-site request forgery (XSRF) and cross-site scripting (XSS) attacks. Leveraging machine learning algorithms, particularly through the developed cyber defense framework - algoXSSF, offers numerous benefits. AlgoXSSF enhances detection accuracy, facilitates real-time threat response, autonomously adapts to evolving threats, minimizes false positives, and streamlines security operations. By harnessing the power of machine learning, algoXSSF serves as a robust defense mechanism against malicious attacks, including Man-in-the-Middle attacks, reinforcing websites and online platforms against cyber threats.

关键词： Machine learning algorithms Social networking (online) Cross-site scripting Surge protection Forgery Security Servers

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：