检索结果-内蒙古大学图书馆

An optimized facial recognition model for identifying criminal activities using deep learning strategy

International Journal of information technology (Singapore) 2023年第7期15卷 3907-3921页

作者： Gokulakrishnan, S. Chakrabarti, Prasun Hung, Bui Thanh Shankar, S. Siva Artificial Intelligence Laboratory Faculty of Information Technology Ton Duc Thang University Ho Chi Minh City Viet Nam Deputy Provost ITM SLS Baroda University Gujarat Vadodara India Department of Computer Science and Engineering KG Reddy College of Engineering and Technology (Autonomous) Telangana Hyderabad India

The most important research field in the current period is facial recognition and detection. Furthermore, facial expression recognition applications are essential in various research areas such as criminal investigation, security, data base management systems (DBMS), innovative card application, and video surveillance systems. A criminal investigation is an important area of study. Thus, in today’s world, crime activities are fast expanding in response to psychological trauma. As a result, applying deep learning (DL) algorithms for face expression identification and crime activity monitoring is a growing area of investigation. In terms of pre-processing, feature extraction, and recognizing diverse facial emotions, DL produces better results. As a result, the current study seeks to offer a revolutionary intelligent Strawberry-based convolution neural network (SbCNN). When applied to the Kaggle face expression database, the created SbCNN technique performed best. Face verification and criminal face detection can be accomplished using this approach and the optimization fitness function. Even though the established design improves the robustness of feature extraction and classification, it is a time-consuming process. © 2023, The Author(s), under exclusive licence to Bharati Vidyapeeth's Institute of computer Applications and Management.

关键词： Data base management system Deep learning Facial recognition and detection Kaggle Optimization Psychological harm Video surveillance systems

来源：评论

学校读者我要写书评

暂无评论

Analysis of PV and EV Chargers Integration Impact on Radial LV Distribution Network

Analysis of PV and EV Chargers Integration Impact on Radial ...

引用

International Multidisciplinary Conference on computer and Energy science (SpliTech)

作者： Marina Dubravac Zvonimir Šimić Danijel Topić Goran Knežević Krešimir Fekete Josip Juraj Strossmayer University of Osijek Osijek Croatia Faculty of Electrical Engineering Computer Science and Information Technology Osijek Osijek Croatia

Recently, there is more and more integration of photovoltaics (PV) and chargers for electric vehicles (EV) in existing low-voltage (LV) distribution networks. Integration of PVs and EV chargers individually can have a negative effect on the electrical variables of radial distribution networks such as voltages, loading of network elements, losses, etc. However, their simultaneous operation mitigates the negative impact caused by their individual integration. In this paper, different levels of PVs and EV chargers integration are considered and their effect on voltages, loading of cables, losses, as well as power exchange with the external network is studied. Simulation scenarios are implemented in DIgSILENT PowerFactory and power flows are analyzed. According to obtained results, the worst scenarios present two marginal scenarios - without PVs and 100% EV chargers and 100% PVs and without EV chargers. Values of observed parameters in these scenarios have the highest deviations from rated values. In scenario with 50% PV and 25% EV chargers integration, voltage deviation from rated voltage, loading of cables and losses have the lowest value.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Low-Complexity Quantum Annealing based Beamforming for Distributed-RIS-Assisted Communication System

Low-Complexity Quantum Annealing based Beamforming for Distr...

引用

2024 IEEE Middle East Conference on Communications and Networking, MECOM 2024

作者： Lin, Fangyu Zhu, Chen Huang, Chongwen Yang, Zhaohui Zhang, Zhaoyang Guan, Yong Liang Muhaidat, Sami Yuen, Chau Debbah, Merouane Zhejiang University College of Information Science and Electronic Engineering Hangzhou310027 China Polytechnic Institute Zhejiang University Hangzhou310015 China Nanyang Technological University School of Electrical and Electronics Engineering 639798 Singapore Khalifa University Department of Electrical Engineering and Computer Science Abu Dhabi127788 United Arab Emirates Khalifa University of Science and Technology KU 6G Research Center PO Box 127788 Abu Dhabi United Arab Emirates

ISBN: (纸本)9798350376715

Reconfigurable intelligent surface (RIS) is increasingly recognized as a pivotal technology for the sixth-generation communication networks, offering a unique ability to customize the communication environment by programming the passive surface. To fully exploit RISs' potential in improving the coverage and spectral efficiency, we focus on the beamforming design for a distributed-RIS-assisted communication system. However, it usually has the high computational complexity and difficulty to obtain the feasible solution due to non-linear constraints of distributed RISs. To solve this highly non-convex optimization problem of multiple variables, we propose a quantum annealing based method in this paper. Specifically, we firstly transform the original sum-of-log problem into a sub-problem in the form of Ising model by using the fractional programming. Then, we present an adiabatic theorem based algorithm for finding the ground state of the Ising model, and implement it on a Dwave's quantum annealing machine. Numerical results validate the effectiveness of our proposed method, demonstrating that the deployment of quantum annealing can significantly reduce the computational complexity from ON2 to O(N), and obtain an 8% performance gain compared with the typical baselines. © 2024 IEEE.

关键词： Convex optimization

来源：评论

学校读者我要写书评

暂无评论

Multi-class classification using a new Bayesian method

引用

Model Assisted Statistics and Applications 2023年第3期18卷 257-266页

作者： Vovan, Tai Nguyenthikim, Hieu Phamtoan, Dinh College of Natural Science Can Tho University Can Tho City Viet Nam Basic Science Faculty Mien Tay Construction University Vinh Long City Viet Nam Faculty of Mechanical-Electrical and Computer Engineering School of Technology Van Lang University Ho Chi Minh City Viet Nam

This paper proposes a new classification model using the Bayes method. This model not only determines the prior probability based on the k-means algorithm, builds the method for estimating the probability density function via the kernel function, but also classifies the objects to the known populations. The proposed model is described via the experiment of image classifying. In this example, we first use the Gray level co-occurrence matrix to extract the features of images, and next classify this data set based on the improved Bayesian method. In another application, we also build the classification problem for the Algerian Forest Fires data set. The outstanding advantages of this method are the adaptive ability of the kernel function, the classification for multi-class, and the reduction of computational costs. In addition, the experimental results also show the potential of the developed model. © 2023 - IOS Press. All rights reserved.

关键词： Bayesian method fuzzy c-mean image classification kernel function

来源：评论

学校读者我要写书评

暂无评论

Pre-trained CNN Based Deep Features with Hand-Crafted Features and Patient Data for Skin Lesion Classification 3rd

Pre-trained CNN Based Deep Features with Hand-Crafted Featur...

引用

3rd International Conference on Intelligent Technologies and Applications, INTAP 2020

作者： Yildirim-Yayilgan, Sule Arifaj, Blend Rahimpour, Masoomeh Hardeberg, Jon Yngve Ahmedi, Lule Faculty of Information Technology and Electrical Engineering NTNU – Norwegian University of Science and Technology Gjøvik Norway Faculty of Electrical and Computer Engineering University of Prishtina Prishtina Catholic University of Leuven Leuven Belgium

ISBN: (纸本)9783030717100

Skin cancer is a major public health problem, with millions newly diagnosed cases each year. Melanoma is the deadliest form of skin cancer, responsible for the most over 6500 deaths each year in the US, and the rates have been rising rapidly over years. Because of this, a lot of research is being done in automated image-based systems for skin lesion classification. In our paper we propose an automated melanoma and seborrheic keratosis recognition system, which is based on pre-trained deep network combined with structural features. We compare using different pre-trained deep networks, analyze the impact of using patient data in our approach, and evaluate our system performance with different datasets. Our results shown us that patient data has impact on characteristic curve metric value with around 2–6% and different algorithm in final classification layer has impact with around 1–4%. © 2021, Springer Nature Switzerland AG.

关键词： Dermatology

来源：评论

学校读者我要写书评

暂无评论

DA 2 Net: a dual attention-aware network for robust crowd counting

DA 2 Net: a dual attention-aware network for robust crowd co...

引用

作者： Zhai, Wenzhe Li, Qilei Zhou, Ying Li, Xuesong Pan, Jinfeng Zou, Guofeng Gao, Mingliang School of Electrical and Electronic Engineering Shandong University of Technology Zibo255000 China School of Electronic Engineering and Computer Science Queen Mary University of London LondonE1 4NS United Kingdom School of Information Science and Engineering Shandong University Qingdao266237 China

Crowd counting in congested scenes is a crucial yet challenging task in video surveillance and urban security system. The performance of crowd counting has been greatly boosted with the rapid development of deep learning. However, robust crowd counting in high-density environment with scale variations remains under-explored. To address this problem, we propose a dual attention-aware network (DA 2Net) for robust crowd counting in dense crowd scene with scale variations. Specifically, the DA 2Net consists of two modules, namely Spatial Attention (SA) module and Channel Attention (CA) module. The SA module focuses on the spatial dependencies in the whole feature map to locate the heads accurately. The CA module attempts to handle the relations between channel maps and highlights the discriminative information in specific channels. Thus, it alleviates the mistaken estimation for background regions. The interactions between SA module and CA module provide the synergy which facilitates the learning of discriminative features with a focus on the essential head region. Experimental results on five benchmark datasets, i.e., ShanghaiTech, UCF_CC_50, UCF-QNRF, WorldExpo’10, and NWPU, demonstrate that the DA 2Net can achieve the state-of-the-art performance on both accuracy and robustness. © 2021, The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature.

关键词： Security systems

来源：评论

学校读者我要写书评

暂无评论

Domain Adaptation with Sample Relation Reinforcement 1

引用

24th International Conference on Web information Systems engineering, WISE 2023

作者： Teng, Shaohua Liu, Wenjie Guo, Ruixi Zhang, Wei Zheng, Zefeng Teng, Luyao Chen, Tongbao School of Computer Science and Technology Guangdong University of Technology Guangzhou510006 China School of Electrical Engineering Xi’an Jiaotong University Xi’an710049 China School of Information Engineering Guangzhou Panyu Polytechnic Guangzhou511483 China School of Advanced Manufacturing Guangdong University of Technology Guangzhou510006 China

ISBN: (数字)9789819972548

ISBN: (纸本)9789819972531

Domain adaptation transfers knowledge from the source domain into the target domain by minimizing the distribution discrepancy between two domains. Recently, existing approaches ignore the position differences between samples within the same class. However, there are still two problems that need to be resolved. Firstly, marginal samples and central samples may interact with each other, which leads to samples within the same class aggregate toward the margin (loss common knowledge) or toward the center (loss specific knowledge). Secondly, large distribution differences may result in degraded performance in classification. To solve these two problems, we propose a domain adaptation method called Sample Relation Reinforcement (SRR). To mitigate the interaction between marginal samples and central samples, marginal samples detection (MSD) and central samples detection (CSD) are proposed. Specifically, MSD propose a triple distances metric among the sample pairs and class centers to detect the marginal samples and learn specific knowledge. CSD utilizes the nearest and second-nearest centroid of samples to detect the central samples and learn common knowledge. In addition, dual centroid detection (DCD) is proposed to alleviate the negative effects of distribution differences, which utilizes the class centers of the source and target domains to classify the target samples. Finally, the experimental results on four datasets demonstrate that the proposed method outperforms other competing approaches significantly. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Reinforcement

来源：评论

学校读者我要写书评

暂无评论

Building a Large-Scale and Wide-Area Quantum Internet Based on an OSI-Alike Model

引用

China Communications 2021年第10期18卷 1-14页

作者： Zhonghui Li Kaiping Xue Jian Li Nenghai Yu Jianqing Liu David S.L.Wei Qibin Sun Jun Lu School of Cyber Security University of Science and Technology of ChinaHefeiAnhui 230027China School of Information Science and Technology University of Science and Technology of ChinaHefeiAnhui 230027China Department of Electrical and Computer Engineering University of Alabama in HuntsvilleHuntsvilleAL 35899USA Department of Computer and Information Science Fordham UniversityBronxNY 10458USA

The theory and experiment of quantum information have been studied extensively in recent years,and the feasibility of quantum communication has been *** the fundamental technology is not yet mature,research on quantum internet should be *** implement quantum internet,an architecture that describes how quantum nodes are linked to form networks and how protocol functions are vertically composed need to be developed *** this paper,we present a novel design of a clusterbased structure to describe how quantum nodes are interconnected,and how the structure can improve the performance of qubit transmission and reduce the network *** idea of the quantum local area network(QLAN)is proposed as an essential component of the quantum ***,each quantum repeater links to neighboring repeaters to form a core network,and multiple QLANs are connected through the core *** core network can be grouped into different hierarchical quantum repeater networks according to needed service *** the sake of interoperability and fast prototyping,we adopt the idea of OSI layering model of the current Internet in the design of quantum ***,we elaborate on the composition of quantum nodes and the realization of end-to-end communication.

关键词： quantum internet entanglement swapping quantum repeater teleportation

来源：评论

学校读者我要写书评

暂无评论

CADRL: Category-aware Dual-agent Reinforcement Learning for Explainable Recommendations over Knowledge Graphs

arXiv

引用

arXiv 2024年

作者： Zheng, Shangfei Yin, Hongzhi Chen, Tong Kong, Xiangjie Hou, Jian Zhao, Pengpeng School of Computer Science and Technology Zhejiang Sci-Tech University China School of Information Technology and Electrical Engineering The University of Queensland Australia College of Computer Science and Technology Zhejiang University of Technology China School of Computer Science and Technology Soochow University China

Knowledge graphs (KGs) have been widely adopted to mitigate data sparsity and address cold-start issues in recommender systems. While existing KGs-based recommendation methods can predict user preferences and demands, they fall short in generating explicit recommendation paths and lack explainability. As a step beyond the above methods, recent advancements utilize reinforcement learning (RL) to find suitable items for a given user via explainable recommendation paths. However, the performance of these solutions is still limited by the following two points. (1) Lack of ability to capture contextual dependencies from neighboring information. (2) The excessive reliance on short recommendation paths due to efficiency concerns. To surmount these challenges, we propose a category-aware dual-agent reinforcement learning (CADRL) model for explainable recommendations over KGs. Specifically, our model comprises two components: (1) a category-aware gated graph neural network that jointly captures context-aware item representations from neighboring entities and categories, and (2) a dual-agent RL framework where two agents efficiently traverse long paths to search for suitable items. Finally, experimental results show that CADRL outperforms state-of-the-art models in terms of both effectiveness and efficiency on large-scale datasets. Copyright © 2024, The Authors. All rights reserved.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

Exploring the Application of Image Restoration Algorithms in Digital Image Processing 1

Exploring the Application of Image Restoration Algorithms in...

引用

1st IEEE International Conference on Emerging Research in Computational science, ICERCS 2023

作者： Singh, Akhilendra Pratap Sara, S. Sakhare, Nitin N. Kumar, Rohit Kumar, P. Kishore Saini, Rajat Maharishi University of Information Technology Maharishi School of Engineering and Technology Uttar Pradesh India Prince Shri Venkateshwara Padmavathy Engineering College Department of Master of Business Administration Chennai127 India Vishwakarma Institute of Information Technology Department of Computer Engineering Pune India Vivekananda Global University Department of Civil Engineering Jaipur India Faculty of Engineering and Technology Department of Electrical and Electronics Engineering Karnataka Bangalore India Chitkara University Institute of Engineering and Technology Chitkara University Centre of Interdisciplinary Research in Business and Technology Punjab India

ISBN: (纸本)9798350359756

Image recovery algorithms are used to enhance the advent of virtual pix. Those algorithms help enhance the picture by casting off low-frequency noise, polishing edges, and minimizing degradation because of camera noise, motion blur, movement aberration, and aerial distortion. Image recuperation algorithms are utilized in virtual picture processing programs, including scientific imaging, satellite to for pc imaging, object reputation, and competent picture evaluation. This paper explores the software of picture healing algorithms in virtual photograph processing to improve the accuracy and exceptional of the end product. Unique algorithms are used to gain the desired results. Furthermore, this paper discusses the blessings and drawbacks of using those algorithms in digital photo processing and gives possible solutions to demanding situations. Finally, the paper provides an outlook on the future of picture restoration algorithms in phrases of studies and algorithms. © 2023 IEEE.

关键词： Image enhancement

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：