检索结果-内蒙古大学图书馆

LS-SIFT: Enhancing the Robustness of SIFT During Pose-Invariant Face Recognition by Learning Facial Landmark Specific Mappings

引用

IEEE Access 2024年 12卷 76648-76662页

作者： Lin, Shinfeng D. Linares Otoya, Paulo E. National Dong Hwa University Department of Computer Science and Information Engineering Hualien Taiwan

The proper functioning of many real-world applications in biometrics and surveillance depends on the robustness of face recognition systems against pose, and illumination variations. In this work, we employ ensemble systems in conjunction with local descriptors to address pose-invariant face recognition (PIFR). Facial landmarks are detected during the first step with a two fold usage. The landmark locations are employed to perform head pose classification (HPC). HPC allows to select only the visible landmarks for further processing. Then, local descriptors are extracted from the selected landmarks within a face image. We are proposing a novel learned descriptor (LS-SIFT) to overcome the robustness limitations of SIFT against large viewpoint variability during face recognition. Second, the extracted descriptors are used to train the base learners comprising an ensemble system for each subject in a face database (one ensemble per subject, one base learner per landmark). A novel GMM-based base learner model, named Mahalanobis Similarity (MS), is introduced in this work. Finally, face recognition is performed based on the ensemble systems' outputs from all the subjects in a face database. During the experimental trials, SIFT and LS-SIFT are employed individually for local feature extraction, whereas GMM and MS are used to build the ensemble systems, in an independent manner, for further comparison. The whole PIFR system is tested on CMU-PIE, Multi-PIE, and FERET databases, outperforming most of the state-of-the-art works regarding images with pose angles in the range of pm 90{o}. © 2013 IEEE.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

DNA Computing with Water Strider Based Vector Quantization for Data Storage Systems

引用

computers, Materials & Continua 2023年第3期74卷 6429-6444页

作者： A.Arokiaraj Jovith S.Rama Sree Gudikandhula Narasimha Rao K.Vijaya Kumar Woong Cho Gyanendra Prasad Joshi Sung Won Kim Department of Networking and Communications College of Engineering and TechnologySRM Institute of Science and TechnologyKattankulathur603203India Department of Computer Science Engineering Aditya Engineering CollegeSurampalemAndhra Pradesh533437India Department of Computer Science and Engineering Vignan’s Institute of Information TechnologyVisakhapatnam530049India Department of Computer Science and Engineering Vignan’s Institute of Engineering for WomenVisakhapatnam530049India Department of Software Convergence Daegu Catholic UniversityGyeongsan38430Korea Department of Computer Science and Engineering Sejong UniversitySeoul05006Korea Department of Information and Communication Engineering Yeungnam UniversityGyeongsan-siGyeongbuk-do38541Korea

The exponential growth of data necessitates an effective data storage scheme,which helps to effectively manage the large quantity of *** accomplish this,Deoxyribonucleic Acid(DNA)digital data storage process can be employed,which encodes and decodes binary data to and from synthesized strands of *** quantization(VQ)is a commonly employed scheme for image compression and the optimal codebook generation is an effective process to reach maximum compression *** article introduces a newDNAComputingwithWater StriderAlgorithm based Vector Quantization(DNAC-WSAVQ)technique for Data Storage *** proposed DNAC-WSAVQ technique enables encoding data using DNA computing and then compresses it for effective data ***,the DNAC-WSAVQ model initially performsDNA encoding on the input images to generate a binary encoded *** addition,aWater Strider algorithm with Linde-Buzo-Gray(WSA-LBG)model is applied for the compression process and thereby storage area can be considerably *** order to generate optimal codebook for LBG,the WSA is applied to *** performance validation of the DNAC-WSAVQ model is carried out and the results are inspected under several *** comparative study highlighted the improved outcomes of the DNAC-WSAVQ model over the existing methods.

关键词： DNA computing data storage image compression vector quantization ws algorithm space saving

来源：评论

学校读者我要写书评

暂无评论

A Novel Eccentric Intrusion Detection Model Based on Recurrent Neural Networks with Leveraging LSTM

引用

computers, Materials & Continua 2024年第3期78卷 3089-3127页

作者： Navaneetha Krishnan Muthunambu Senthil Prabakaran Balasubramanian Prabhu Kavin Kishore Senthil Siruvangur Kavitha Chinnadurai Jehad Ali Department of Computer Applications Karpagam College of EngineeringCoimbatore641032India Department of Computer Science and Engineering Karpagam College of EngineeringCoimbatore641032India Department of Data Science and Business Systems College of Engineering and TechnologySRM Institute of Science and TechnologyKattankulathur603203India Department of Computer Science and Engineering Sathyabama Institute of Science and TechnologyJeppiaar NagarRajiv Gandhi SalaiChennai600119India Department of AI Convergence Network Ajou UniversitySuwon16499Korea

The extensive utilization of the Internet in everyday life can be attributed to the substantial accessibility of online services and the growing significance of the data transmitted via the ***,this development has expanded the potential targets that hackers might *** adequate safeguards,data transmitted on the internet is significantly more susceptible to unauthorized access,theft,or *** identification of unauthorised access attempts is a critical component of cybersecurity as it aids in the detection and prevention of malicious *** research paper introduces a novel intrusion detection framework that utilizes Recurrent Neural Networks(RNN)integrated with Long Short-Term Memory(LSTM)*** proposed model can identify various types of cyberattacks,including conventional and distinctive *** networks,a specific kind of feedforward neural networks,possess an intrinsic memory *** Neural Networks(RNNs)incorporating Long Short-Term Memory(LSTM)mechanisms have demonstrated greater capabilities in retaining and utilizing data dependencies over extended *** such as data types,training duration,accuracy,number of false positives,and number of false negatives are among the parameters employed to assess the effectiveness of these models in identifying both common and unusual *** are utilised in conjunction with LSTM to support human analysts in identifying possible intrusion events,hence enhancing their decision-making capabilities.A potential solution to address the limitations of Shallow learning is the introduction of the Eccentric Intrusion Detection *** model utilises Recurrent Neural Networks,specifically exploiting LSTM *** proposed model achieves detection accuracy(99.5%),generalisation(99%),and false-positive rate(0.72%),the parameters findings reveal that it is superior to state-of-the-art techniques.

关键词： Cybersecurity intrusion detection machine learning leveraging long short-term memory(LLSTM) CICIDS2019 dataset innovative cyberattacks

来源：评论

学校读者我要写书评

暂无评论

A New Alliance of Machine Learning and Quantum Computing: Concepts, Attacks, and Challenges in IoT Networks

引用

IEEE Internet of Things Journal 2025年第12期12卷 18865-18886页

作者： Rishiwal, Vinay Agarwal, Udit Yadav, Mano Tanwar, Sudeep Garg, Deepak Guizani, Mohsen MJP Rohilkhand University Department of Computer Science and Information Technology Bareilly India Bareilly College Bareilly Department of Computer Science India Nirma University Institute of Technology Department of Computer Science and Engineering Gujarat Ahmedabad382481 India SR University School of Computer Science and Artificial Intelligence Telangana- Warangal506371 India Abu Dhabi United Arab Emirates

The Internet of Things (IoT) is a constantly expanding system connecting countless devices for seamless data collection and exchange. This has transformed decision-making with data-driven insights across different domains. However, challenges arise concerning security and computational limitations. To strengthen IoT against cyber threats and optimize resource usage, combining Quantum Computing with Machine Learning (ML) is a promising approach. ML enables computers to learn from data and detect patterns without explicit programming. By leveraging ML algorithms, vast datasets from IoT devices can be analyzed, identifying anomalies and forecasting potential security breaches. Yet, conventional ML algorithms may need help with the complexity and scale of IoT data. Quantum Computing, based on quantum mechanics, offers unparalleled computational speed and scale. Quantum ML algorithms can quickly analyze IoT datasets, identifying patterns and potential threats. This study examines the ideas behind ML, quantum computing, and their potential collaboration within IoT networks. The research focuses on the possibility of improving the security of IoT networks by integrating quantum computing approaches with ML. It also addresses the challenges and limitations of integrating ML and quantum computing in the context of IoT networks. These obstacles include hardware constraints, algorithm complexities, and the need for specialized knowledge. © 2025 IEEE.

关键词： Quantum computers

来源：评论

学校读者我要写书评

暂无评论

TISCMB: design of a highly efficient blockchain consensus model with trust integrated self-correcting miner selection

引用

International Journal of information technology (Singapore) 2023年第4期15卷 1845-1858页

作者： Ravi Kumar, Shipra Goyal, Mukta Department of Computer Science Engineering and Information Technology Jaypee Institute of Information Technology Noida India

Blockchain is rapidly becoming the de facto standard for storage applications requiring high transparency, record traceability, immutable data, and distributed processing. Researchers have proposed a large number of such models, including Proof-of-Work (PoW), Proof-of-Stake (PoS), Proof-of-Authority (PoA), etc. Due to their respective limitations, each of these models is applied to context-specific blockchain deployments. In addition, the selection of the most efficient miners for hash calculation and verification is a complex task that must be executed with high efficiency in order to improve network performance. The novel contribution of this work is to design a hybrid consensus model which uses a combination of Proof-of-Work and Proof-of-Stake consensus methods for fast hash computations. Proposed model is supported by a highly efficient trust-based miner selection method that aids in choosing the most optimal miner nodes with low processing delay and high energy efficiency. In addition, this text proposes a self-correcting mechanism for the designed blockchain, which assists in the blockchain's correction in the event of any internal or external attacks. Due to these characteristics, it is observed that the proposed model has 20% less delay, 8% less energy consumption, and 15% higher levels of trust than standard PoS and PoW consensus models. The model was also subjected to various attack scenarios, and it was determined that it is capable of self-correcting the node's internal blockchain with a 99.9% success rate, thereby enhancing its real-time deployment capabilities. © 2023, The Author(s), under exclusive licence to Bharati Vidyapeeth's Institute of computer Applications and Management.

关键词： Blockchain Consensus Delay Energy Self-correcting Trust

来源：评论

学校读者我要写书评

暂无评论

Preserving friendly stacking and weighted shadows in selective scalable secret image sharing

引用

Multimedia Tools and Applications 2023年第19期82卷 29283-29305页

作者： Lee, Jung-San Chen, Yin-Chin Hsieh, Yun-Hao Chang, Shih-Hao Huynh, Ngoc-Tu Department of Information Engineering and Computer Science Feng Chia University Taichung40724 Taiwan Department of Computer Science and Information Engineering National Taipei University of Technology Taipei Taiwan Department of Information Technology Ton Duc Thang University Ho Chi Minh City Viet Nam

With advancement of technology, the technique of selective scalable secret image sharing (SSSIS) was first proposed in 2017 as a new alternative of secret image sharing. The region of interest (ROI) in the protected secret could be revealed progressively once the number of collected shadows has reached a predefined threshold. Accordingly, the ROIs of the secret image increase based on the number of collected shadows. Nonetheless, players without sufficient shadows may be able to learn the location and contour of hidden secret to perform advanced guessing attacks. Thus, we aim to introduce friendly stacking to yield a genuine outcome of mitigating this risk during the recovery process. Furthermore, the weighting concept is brought into constructing the meaningful shadow so that the priority of a specific participant can be emphasized to approach real applications. © 2023, The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Efficient 3D Tracking and Detection of Multi-Rotor UAVs Using mmWave Radar with Semi-Supervised Learning

引用

IEEE Sensors Journal 2025年第12期25卷 22001-22014页

作者： Xi, Rui Wei, Wenjie Zhang, Malu University of Electronic Science and Technology of China Department of Computer Science and Engineering Chengdu611731 China

Small UAVs pose security risks to sensitive areas and individuals due to their rapid movement and wide coverage capabilities. Effective monitoring necessitates the deployment of lightweight and energy-efficient surveillance systems. This research introduces an efficient 3D tracking and detection approach for small UAVs, utilizing millimeter-wave radars and Spiking Neural Networks (SNNs). By capturing micro-Doppler characteristics of UAV movements, it effectively processes low signal-to-noise ratios and uncertain signals. An improved angle estimation algorithm, combining dynamic programming and particle filters, enables realtime 3D UAV tracking with reduced computational complexity. Then, a simple UAV detection model based on SNN architecture is developed by leveraging UAVs’ position and corresponding Doppler information. Furthermore, a bio-inspired semi-supervised method is proposed to facilitate the training of SNNs using a limited number of annotated samples. The effectiveness of the proposed methodology is evaluated under various environmental conditions. Results indicate a significant improvement in tracking computation time efficiency, with the recognition model size reduced to one-tenth of its original size, yet it maintains near-original system performance. © 2001-2012 IEEE.

关键词： Semi-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Optimizing Technical Analysis and Stock Price Analysis Using: BLRM-QNDNL 21

Optimizing Technical Analysis and Stock Price Analysis Using...

引用

21st OITS International Conference on information technology, OCIT 2023

作者： Kalva, Sudhakar Naganjaneyulu, Satuluri Sudhakar, K. Computer Science and Engineering Department of Information Technology Department of Computer Science and Engineering Kurnool India

ISBN: (纸本)9798350358230

The Stock value forecast is a significant issue to determine the future direction of the financial Markets. Many research works are carried out and design many techniques to predict stock price of Individual stocks. But, the forecast precision/ of the regular methods was lower when taking the enormous size of the dataset. To address this downside, a Novel Deep Learning based Broken-Stick Linear Regressive MapReduce Based on Quasi-Newton Deep Neural Learning (BLRM-QNDNL) method is proposed right now. BLRM-QNDNL technique targeting optimizing the parameters engaged with stock profit prediction. Quasi-Newton based Deep Neural Network Learning (Q-NDNL) is applied in the BLRM-QNDNL procedure for precisely foreseeing the stock prices dependent on the news with higher accuracy. Q-NDNL used several hidden layer in order to thoroughly examine the effects of emotions conveyed in news items on stocks with the least amount of time complexity. The BLRM-QNDNL method expands the stock price forecast performance with lower time complexity when compared with cutting edge works. The BLRM-QNDNL technique has been evaluated exploratory on metrics such as prediction accuracy, prediction time, and false positive rate with regard to different numbers of data. When compared to state-of-the-art studies, the experimental results show that the BLRM-QNDNL technique can reduce the time complexity of stock price prediction while simultaneously increasing its accuracy. The suggested BLRM-QNDNL technique reduces the false positive stock price prediction rate by 41% and 57%, respectively and decreases market price prediction time complexity by 9 percent and 29 percent relative to traditional DeepClue [1] and MFNN [2], respectively. © 2023 IEEE.

关键词： MapReduce

来源：评论

学校读者我要写书评

暂无评论

Revealing inputs causing web API performance latency using response-time-guided genetic algorithm fuzzing

引用

Artificial Life and Robotics 2024年第4期29卷 459-472页

作者： Huang, Ying-Tzu Lee, Shin-Jie Department of Computer Science and Information Engineering National Cheng Kung University Tainan Taiwan

Web APIs are integral to modern web development, enabling service integration and automation. Ensuring their performance and functionality is critical, yet performance testing is less explored due to the difficulty in detecting performance bugs. This paper presents a response time-guided genetic algorithm (GA) fuzzing approach to uncover web API performance latency in a black-box setting. Unlike traditional random input generation, our method uses GA to refine inputs through crossover and mutation, guided by response time-based fitness. We propose two seed generation methods: pairwise combinatorial testing using Mircosoft’s Pairwise Independent Combinatorial Testing (PICT) and randomly paired combinations. We compared our method with classic random fuzzing. Experiments on five real-world web APIs show that our approach significantly outperforms classic random fuzzing, identifying inputs with response times 1.5 to 26.3 times longer. Additionally, PICT-generated seeds demonstrated superior performance compared to randomly-paired combinations in 2 out of 5 APIs. Our findings highlight the potential of GA-based fuzzing to reveal web API performance latency, advocating for further research in this area. © International Society of Artificial Life and Robotics (ISAROB) 2024.

关键词： Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

Escape Routing Using Deep Reinforcement Learning

Escape Routing Using Deep Reinforcement Learning

引用

2025 International Workshop on Advanced Imaging technology, IWAIT 2025

作者： Cheng, Hsu Fu Cheng, Dun Wei Department of Computer Science and Information Engineering National Yunlin University of Science & Technology Yunlin Taiwan

ISBN: (数字)9781510688131

ISBN: (纸本)9781510688124

Escape routing is a critical task in the design of printed circuit boards (PCB) and integrated circuits (IC), aiming to establish effective connections among multiple pin points while avoiding path overlaps and interference from *** paper proposes a Deep Reinforcement Learning (DRL)-based solution utilizing a Deep Q-Network (DQN) to address the escape routing *** problem is modeled as a Markov Decision Process (MDP), and the agent learns effective routing strategies through interactions with the *** were conducted in a 25×26 simulated grid environment, testing scenarios with 30, 60, and 90 pin *** study highlights the potential of Deep Reinforcement Learning in solving escape routing problems, offering a novel approach to addressing routing challenges in PCB design. © 2024 SPIE.

关键词： Deep reinforcement learning

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：