检索结果-内蒙古大学图书馆

Incremental Instance Segmentation for Cluttered Baggage Threat Detection

Incremental Instance Segmentation for Cluttered Baggage Thre...

2023 IEEE International Conference on Computational Intelligence and Virtual Environments for Measurement Systems and Applications, CIVEMSA 2023

作者： Nasim, Ammara Velayudhan, Divya Ahmed, Abdelfatah Hassan Hassan, Taimur Akcay, Samet Akram, Muhammad Usman Werghi, Naoufel National University of Sciences and Technology Department of Computer and Software Engineering Pakistan Khalifa University KUCARS and C2PS Department of Electrical Engineering and Computer Science United Arab Emirates Abu Dhabi University Department of Electrical and Computer Engineering Abu Dhabi United Arab Emirates Intel Corporation RandD Division United Kingdom

ISBN: (纸本)9781665434454

Identification of contraband items from highly oc-cluded baggage of air travelers is a challenging task even for human experts with very high experience. Many researchers have been working rigorously to develop computer vision-based techniques for baggage screening through X-ray images. Nu-merous machine learning and deep learning-based frameworks have been proposed by researchers in the last two decades. However, all of these techniques face limitations in segmenting prohibited items from highly occluded and cluttered baggage. In this paper, we propose a novel framework based on semantic segmentation to automatically detect concealed prohibited items from X-ray baggage scans. Furthermore, to detect different overlapping instances of the same contraband item, we propose an instance-Aware segmentation model that enables the semantic segmentation model to identify multiple instances of the same threat category through incremental learning without requiring additional overhead. The proposed framework is computationally lighter compared to other similar approaches as it requires min-imal training examples and leverages previous knowledge. The proposed model has outperformed state-of-The-Art instance seg-mentation techniques when tested on publicly available GDXray and SIXray datasets, giving mean average precision scores of 0.50 and 0.47, respectively. In addition, the proposed framework leads other instance segmentation baseline models in terms of mean inference time. © 2023 IEEE.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Decentralized Adaptive Routing Framework using Q-Learning and Blockchain

Decentralized Adaptive Routing Framework using Q-Learning an...

引用

Pervasive Computing and Social Networking (ICPCSN), International Conference on

作者： Esswari S Salaja Silas G. Jaspher W. Kathrine Computer Science and Engineering Karunya Institute of Technology and Sciences Coimbatore Division of CSE Karunya Institute of Technology and Sciences Coimbatore

ISBN: (数字)9798331535193

ISBN: (纸本)9798331535209

Efficient and reliable routing in decentralized networks remains a persistent challenge, particularly in environments characterized by dynamic and unpredictable conditions. Traditional routing protocols often lack the adaptability required to respond effectively to rapid changes, leading to suboptimal performance and increased latencies [1] [2]. A decentralized routing framework is proposed, integrating Proof-of-Authority (PoA) blockchain for secure and transparent transaction logging [3] with a multi-neighbor Q-learning algorithm for adaptive decision-making [4] [5]. By leveraging Q-learning, nodes dynamically optimize their routing choices based on latency feedback while balancing exploration and exploitation [6]. The framework is evaluated within a "2-step ring" topology, demonstrating its ability to adaptively select neighbors while maintaining security and decentralization [7]. Results illustrate significant improvements in routing efficiency, adaptability, and decision robustness across multiple operational cycles, offering a scalable solution for modern network challenges [8] [9]

关键词： Q-learning Adaptive systems Heuristic algorithms Routing Stability analysis Blockchains Topology Security Tuning Thermal stability

来源：评论

学校读者我要写书评

暂无评论

Hemochromatosis Pathogenesis and Its Association with Liver Disease: An Analysis Through Machine Learning 4

Hemochromatosis Pathogenesis and Its Association with Liver ...

引用

4th International Conference on Emerging Trends in Networks and computer Communications, ETNCC 2024

作者： Imtiaz, Isra Rehman, Attique Ur Javaid, Sabeen Ali, Tahir Muhammad Mir, Azka Masud, Mehedi Kumar, Deepak University of Sialkot Department of Software Engineering Sialkot Pakistan Gulf University for Science and Technology Department of Computer Science Kuwait Taif University Department of Computer Science Saudi Arabia Lovely Professional University Division of Research and Development Phagwara144411 India KKR and KSR Institute of Technology and Sciences Andhra Pradesh Guntur India

ISBN: (纸本)9798350353266

A significant risk factor for the development of liver disease is hemochromatosis, an inherited iron overload illness, but the complex pathophysiology behind this link is still unknown. To understand the intricate interactions between hemochromatosis and liver disease, this study uses a cutting-edge strategy that incorporates machine learning techniques. Promising prediction skills are demonstrated by machine learning models, which open up new possibilities for early detection and individualized intervention approaches. The results shed important light on the relationship between hemochromatosis and liver disease and improve our understanding of the pathogenesis of the disease. This study clarifies the pathophysiology of hemochromatosis and its subsequent connection to liver disease, highlighting the revolutionary power of machine learning in understanding intricate biological processes. This selected dataset contains 15 parameters and has 202 dated records with a target value of 'Disease Name' which has 5 different categories Type 1, 2, 2A, 2B,2C, 3, 4, and Type5. The experiment is performed using two classifiers including KNN and Naïve Bayes. The k-fold cross-validation technique is also used to improve the performance. After the comparative analysis of the resulting accuracy percentage of different classifiers, we have proposed the model with the classifier with the highest accuracy. Our proposed model has achieved an accuracy rate of 98.00% using a K-NN classifier. Rapid miner platform is used for the application of the machine learning tools and techniques for this research These discoveries have consequences that go beyond clarifying the mechanisms behind disease;they also open the door to better clinical care and tailored treatment therapies for high-risk people. © 2024 IEEE.

关键词： Potassium alloys

来源：评论

学校读者我要写书评

暂无评论

Quickest Detection of Adversarial Attacks Against Correlated Equilibria 39

Quickest Detection of Adversarial Attacks Against Correlated...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Kazari, Kiarash Kanellopoulos, Aris Dán, György Division of Network and Systems Engineering School of Electrical Engineering and Computer Science KTH Royal Institute of Technology Stockholm Sweden

ISBN: (纸本)157735897X

We consider correlated equilibria in strategic games in an adversarial environment, where an adversary can compromise the public signal used by the players for choosing their strategies, while players aim at detecting a potential attack as soon as possible to avoid loss of utility. We model the interaction between the adversary and the players as a zero-sum game and we derive the maxmin strategies for both the defender and the attacker using the framework of quickest change detection. We define a class of adversarial strategies that achieve the optimal trade-off between attack impact and attack detectability and show that a generalized CUSUM scheme is asymptotically optimal for the detection of the attacks. Our numerical results on the Sioux-Falls benchmark traffic routing game show that the proposed detection scheme can effectively limit the utility loss by a potential adversary. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Advanced extended-term simulation approach with flexible quas-isteady-state and dynamic semi-analytical simulation engines

iEnergy

引用

iEnergy 2022年第1期1卷 124-132页

作者： Rui Yao Dongbo Zhao A.P.Sakis Meliopoulos Chanan Singh Joydeep Mitra Feng Qiu Division of Energy Systems Argonne National LaboratoryLemontIL 60439USA School of Electrical and Computer Engineering Georgia Institute of TechnologyAtlantaGA 30332USA Department of Electrical and Computer Engineering Texas A&M UniversityCollege Sta-tionTX 77843USA Department of Electrical and Computer Engineering Michigan State UniversityEast LansingMI 48824USA

Power system simulations that extend over a time period of minutes,hours,or even longer are called extendedterm *** power systems evolve into complex systems with increasing interdependencies and richer dynamic behaviors across a wide range of timescales,extendedterm simulation is needed for many power system analysis tasks(e.g.,resilience analysis,renewable energy integration,cascading failures),and there is an urgent need for efficient and robust extendedterm simulation *** conventional approaches are insufficient for dealing with the extendedterm simulation of multitimescale *** paper proposes an extendedterm simulation approach based on the semianalytical simulation(SAS)*** accuracy and computational efficiency are backed by SAS's high accuracy in eventdriven simulation,larger and adaptive time steps,and flexible switching between fulldynamic and quasisteadystate(QSS)*** used this proposed extendedterm simulation approach to evaluate bulk power system restoration plans,and it demonstrates satisfactory accuracy and efficiency in this complex simulation task.

关键词： Extended-term simulation resilience multi-timescale simulation event-driven simulation dynamics quasi-steady-state(QSS) hybrid simulation holomorphic embedding(HE) semi-analytical simulation(SAS)

来源：评论

学校读者我要写书评

暂无评论

Low Noise Millimeter-Wave Generation with Integrated Lasers and a Compact Fabry-Perot

Low Noise Millimeter-Wave Generation with Integrated Lasers ...

引用

CLEO: Science and Innovations in CLEO 2024, CLEO: S and I 2024 - Part of Conference on Lasers and Electro-Optics

作者： Groman, William Kudelin, Igor Lind, Alexander Lee, Dahyeon Nakamura, Takuma Kelleher, Megan McLemore, Charles A. Guo, Joel Jin, Warren Bowers, John Quinlan, Franklyn Diddams, Scott A. Department of Physics University of Colorado BoulderCO United States Time and Frequency Division National Institute of Standards and Technology BoulderCO United States Department of Electrical and Computer Engineering University of California Santa BarbaraCA United States Department of Electrical Computer and Energy Engineering University of Colorado BoulderCO United States

We generate millimeter-waves up to 118 GHz via heterodyning two photonic chip lasers which are phase-locked to the same miniature F-P cavity. Phase noise as low as −120 dBc/Hz at 40 kHz offset is achieved. © Opti... 详细信息

关键词： Fabry-Perot interferometers

来源：评论

学校读者我要写书评

暂无评论

DEGAP: Dual Event-Guided Adaptive Prefixes for Templated-Based Event Argument Extraction with Slot Querying 31

DEGAP: Dual Event-Guided Adaptive Prefixes for Templated-Bas...

引用

31st International Conference on Computational Linguistics, COLING 2025

作者： Wang, Guanghui Liu, Dexi Nie, Jian-Yun Wan, Qizhi Hu, Rong Liu, Xiping Liu, Wanlong Liu, Jiaming School of Information Management Jiangxi University of Finance and Economics China Canada School of Computer Science and Engineering University of Electronic Science and Technology of China China Department of Statistics Division of the Physical Sciences The University of Chicago United States

ISBN: (纸本)9798891761964

Recent advancements in event argument extraction (EAE) involve incorporating useful auxiliary information into models during training and inference, such as retrieved instances and event templates. These methods face two challenges: (1) the retrieval results may be irrelevant and (2) templates are developed independently for each event without considering their possible relationship. In this work, we propose DEGAP to address these challenges through a simple yet effective components: dual prefixes, i.e. learnable prompt vectors, where the instance-oriented prefix and template-oriented prefix are trained to learn information from different event instances and templates. Additionally, we propose an event-guided adaptive gating mechanism, which can adaptively leverage possible connections between different events and thus capture relevant information from the prefix. Finally, these event-guided prefixes provide relevant information as cues to EAE model without retrieval. Extensive experiments demonstrate that our method achieves new state-of-the-art performance on four datasets (ACE05, RAMS, WIKIEVENTS, and MLEE). Further analysis shows the impact of different components. © 2025 Association for Computational Linguistics.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

Novel Functional Community Detection in Networked Smart Grid Systems-Based Improved Louvain Algorithm

Novel Functional Community Detection in Networked Smart Grid...

引用

2023 IEEE Texas Power and Energy Conference, TPEC 2023

作者： Eddin, Maymouna Ez Massaoudi, Mohamed Abu-Rub, Haitham Shadmand, Mohammad Abdallah, Mohamed Texas A&M University at Qatar Department of Electrical and Computer Engineering Doha Qatar Texas A&M University Department of Electrical and Computer Engineering College Station United States University of Illinois at Chicago Department of Electrical and Computer Engineering Chicago United States Hamad Bin Khalifa University Division of Information and Computing Technology College of Science and Engineering Doha Qatar

ISBN: (纸本)9781665490719

Despite using Community Detection Algorithms (CDA) in various network partitioning real-world applications, these algorithms tend to fail to partition complex weighted functional networks such as power grids. When contingency events occur, appropriate power grid partitioning enables an effective distributed control strategy to detect system faults and cyberattacks and accelerate electrical assets recovery through fast remedial control. This paper addresses the CDA by considering the functional structure of the power grid. When comparing the topological and functional structures of the power grid network, Electrical Coupling Strength (ECS) reflects both direct and indirect power flows, unlike a conventional adjacency matrix, which only considers an unweighted direct connection between buses. The proposed Improved Louvain Algorithm (ILA) employs the ECS patterns to represent the network connection. Here, the quality function is modified as electrical modularity Qe to assess the goodness of the produced clusters. Large Qe indicates that the power transmission within the partition is dense compared to power transmission with other partitions. The algorithm has been tested on IEEE 39-bus and 118-bus systems. Using different case scenarios, the simulation results demonstrate the high effectiveness of the proposed ILA to the traditional Louvain algorithm in partitioning the complex networked electrical grid into adequate subsystems. © 2023 IEEE.

关键词： Intrusion detection

来源：评论

学校读者我要写书评

暂无评论

Prognostic Kalman Filter Based Bayesian Learning Model for Data Accuracy Prediction

引用

computers, Materials & Continua 2022年第7期72卷 243-259页

作者： S.Karthik Robin Singh Bhadoria Jeong Gon Lee Arun Kumar Sivaraman Sovan Samanta A.Balasundaram Brijesh Kumar Chaurasia S.Ashokkumar Department of ECE College of Engineering and TechnologySRM Institute of Science and TechnologyVadapalaniChennai600026India Department of CSE Birla Institute of Applied Sciences(BIAS)BhimtalUttarakhand263136India Division of Applied Mathematics Wonkwang University460Iksan-DaeroIksan-SiJeonbuk54538Korea School of Computer Science and Engineering Vellore Institute of Technology(VIT)Chennai600127India Department of Mathematics Tamralipta MahavidyalayaWest Bengal721636India School of Computer Science and Engineering Center for Cyber Physical SystemsVellore Institute of Technology(VIT)Chennai600127India Indian Institute of Information Technology(IIIT) LucknowUttar Pradesh226002India Department of Computer Science and Engineering Saveetha School of EngineeringSIMATSChennai602105India

Data is always a crucial issue of concern especially during its prediction and computation in digital *** paper exactly helps in providing efficient learning mechanism for accurate predictability and reducing redundant data *** also discusses the Bayesian analysis that finds the conditional probability of at least two parametric based predictions for the *** paper presents a method for improving the performance of Bayesian classification using the combination of Kalman Filter and *** method is applied on a small dataset just for establishing the fact that the proposed algorithm can reduce the time for computing the clusters from *** proposed Bayesian learning probabilistic model is used to check the statistical noise and other inaccuracies using unknown *** scenario is being implemented using efficient machine learning algorithm to perpetuate the Bayesian probabilistic *** also demonstrates the generative function forKalman-filer based prediction model and its *** paper implements the algorithm using open source platform of Python and efficiently integrates all different modules to piece of code via Common Platform Enumeration(CPE)for Python.

关键词： Bayesian learning model kalman filter machine learning data accuracy prediction

来源：评论

学校读者我要写书评

暂无评论

Fast-acting halide-perovskite-based RGB fluorescent materials for aggregate Gb/s visible light communication 20

Fast-acting halide-perovskite-based RGB fluorescent material...

引用

Optical Components and Materials XX 2023

作者： Wang, Yue Wang, Hong Alkhazragi, Omar Mohammed, Zyad O.F. Gutiérrez-Arzaluz, Luis Kang, Chun Hong Ng, Tien Khee Mohammed, Omar F. Ooi, Boon S. Photonics Laboratory Division of Computer Electrical and Mathematical Sciences and Engineering King Abdullah University of Science and Technology Thuwal23955-6900 Saudi Arabia Membranes and Porous Materials Center KAUST Catalysis Center Division of Physical Science and Engineering King Abdullah University of Science and Technology Thuwal23955-6900 Saudi Arabia

ISBN: (纸本)9781510659391

Three types of halide-perovskite-based fast-acting fluorescent materials have been demonstrated for high-speed visible light communication. All-inorganic metal-halide perovskite CsPbI3 was utilized to generate red color at 685 nm, and two-dimensional (2D) hybrid organic-inorganic halide perovskite nanosheets, (PEA)2PbI4 and (PEA)2PbBr4 (PEA= C8H9NH3), with peak photoluminescence (PL) wavelengths of 525 nm and 408 nm, were respectively used for green- and blue-light emission. The materials were then embedded in the polymethyl methacrylate (PMMA) to improve their durability and flexibility in practical applications. Pumped by a 405-nm violet laser, the red and green phosphors exhibit –3-dB modulation bandwidths of 14 MHz and 193 MHz, respectively. For the blue phosphor, a 124-MHz –3-dB bandwidth was obtained by using a 375-nm UVA laser diode. Benefitting from either the short PL lifetime or high PL quantum yield, aggregate Gb/s data transmission was achieved in the communication link. Direct current biased optical orthogonal frequency-division multiplexing (DCO-OFDM) modulation scheme was implemented with an adaptive quadrature amplitude modulation (QAM) signal. The transmission net data rates of RGB phosphors are 0.51 Gb/s, 0.93 Gb/s, and 0.43 Gb/s, respectively. The corresponding average bit error ratios are 3.5×10-3, 3.6×10-3, and 3.6×10-3, which are below the 7%-overhead forward error correction (FEC) criterion. Taking advantage of the tunability of the halide perovskite materials covering the whole visible range could further fulfill high-speed color-pure wavelength-division multiplexing by using a single source with multiple luminescent materials emitting light at different wavelengths. Besides, combining luminescent materials with specific colors, simultaneous white-light illumination, and high-speed communication can also be realized. © 2023 SPIE.

关键词： Perovskite

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：