检索结果-内蒙古大学图书馆

IAENG International Journal of computer science 2021年第2期48卷 1-9页

作者： Sun, Wei-Zhong Zhang, Min Wang, Jie-Sheng Guo, Sha-Sha Wang, Min Hao, Wen-Kuo A lecturer of School of Computer Science and Software Engineering University of Science and Technology Liaoning Anshan114051 China A postgraduate student of School of Electronic and Information Engineering University of Science and Technology Liaoning Anshan114051 China A professor of School of International Finance and Banking University of Science and Technology Liaoning Anshan114051 China

Binary particle swarm optimization (BPSO) algorithm can map the original continuous searching space to the binary searching space by introducing a new velocity transfer function. For the 0-1 knapsack problem, a binary particle swarm optimization algorithm based on the Z-shaped probability transfer function was proposed. In order to solve the shortcomings of BPSO algorithm based on S-shaped and V-shaped probability functions that it is easy to fall into local optima and slow convergence speed, a new probability function (Z-shaped transfer function) was proposed. Then a penalty function strategy is adopted to deal with the violation of the constraint solutions. In order to verify the effectiveness of the proposed algorithm, the BPSO algorithm based on the Z-shaped transfer function with different parameters was used to solve the typical 0-1 knapsack problems, which is compared with the BPSO algorithm based on the S-shape and the V-shape transfer functions. Simulation experiment results show that the proposed Z-shaped probability transfer function improves the convergence speed and optimization accuracy of the BPSO algorithm. © 2021. All Rights Reserved.

关键词： Transfer functions

来源：评论

学校读者我要写书评

暂无评论

Identification and Classification of Rare Medicinal Plants

Identification and Classification of Rare Medicinal Plants

引用

International Conference on Emerging Trends in Networks and computer Communications (ETNCC)

作者： Piyush Singh Bora Shamneesh Sharma Isha Batra Arun Malik Farzeen Ashfaq School of Computer Science and Engineering Lovely Professional University Punjab India Delivery and Student Success upGrad Campus upGrad Education Private Limited Bangalore India School of Computer Science Taylor's University Subang Jaya Malaysia

ISBN: (数字)9798350353266

ISBN: (纸本)9798350353273

The identification and conservation of rare medicinal plants are crucial, given their invaluable role in healthcare, pharmaceuticals, and biodiversity preservation. Numerous varieties face extinction according to the International Union for Conservation of Nature (IUCN), necessitating advanced image processing and computer vision techniques for accurate identification and documentation. This paper presents a novel deep learning approach leveraging convolutional neural networks (CNNs) and transfer learning to adapt the MobileNet V2 architecture for automated identification and classification of rare medicinal plants found in different areas, utilizing a curated dataset of 6,900 images across 80 distinct classes. The robust deep learning model extracts discriminative visual features from digital images, facilitating accurate taxonomic classification, and outperforming traditional techniques and shallow models. The proposed system empowers stakeholders with reliable accessible tools and plays a pivotal role in biodiversity conservation and sustainable utilization, ensuring nature's therapeutic bounty for generations.

关键词： Medicinal plants Deep learning Adaptation models Technological innovation Accuracy Medical services Mobile applications Environmental management Biomedical imaging Pharmaceuticals

来源：评论

学校读者我要写书评

暂无评论

StorySpinner: AI Based Technique to Narrate the Web Links

StorySpinner: AI Based Technique to Narrate the Web Links

引用

International Conference on Emerging Trends in Networks and computer Communications (ETNCC)

作者： Prajwal Kumbar Shamneesh Sharma Isha Batra Arun Malik Farzeen Ashfaq School of Computer Science and Engineering Lovely Professional University Punjab India Delivery and Student Success upGrad Campus upGrad Education Private Limited Bangalore India School of Computer Science Taylor's University Subang Jaya Malaysia

ISBN: (数字)9798350353266

ISBN: (纸本)9798350353273

The rapid advancement of LLM has facilitated a variety of large language model applications in natural language processing. This report details the development of StorySpinner, an application based on large language models and retrieval-augmented generation that allows yield from articles to the format of an interesting narrative. Moreover, the model addresses processing issues related to the specifics of diverse Internet re-sources, webpages, blogs, and even YouTube videos, by combining web scraping methods, text summarization models, and semantic paragraphs with the use of the extraction of material from extracted abstracts into LLM. The present research investigated the specifics of StorySpinner architecture, the used techniques of information extraction, summarization, and narrative generation, and possible applications of this technology such as educational purposes, accessibility issues, and content development. The paper also provided a discussion of ethical aspects, including bias prevention, copyright issues, and AI technology influence on society. StorySpinner was introduced as a method to fill the gap between web content and human understanding, offering a new way to access information as a story.

关键词： Video on demand Large language models Prevention and mitigation Semantics Text summarization Market research Natural language processing Internet Web sites Videos

来源：评论

学校读者我要写书评

暂无评论

Image Security Utilizing Hybrid Model of Steganography and Asymmetric Cryptography Methods

Image Security Utilizing Hybrid Model of Steganography and A...

引用

2023 International Conference on Intelligent Data Communication Technologies and Internet of Things, IDCIoT 2023

作者： Arora, Himanshu Agarwal, Radhika Sharma, Priyanka Shankar, Gori Arora, Deepti Arya Institute of Engineering and Technology Department of Computer Science and Engineering Rajasthan Jaipur India Maharaja Sawai Man Singh Vidyalaya Student of 12th Class Rajasthan Jaipur India Jaipur Engineering College Department of Mathematics Rajasthan Jaipur India Jaipur Engineering College Department of Electronics and Communication Rajasthan Jaipur India Arya Institute of Engineering and Technology Department of Mathematics Rajasthan Jaipur India

ISBN: (纸本)9781665474511

With the recent technologies, digital data is mostly used in every communication and data transferring process. Moreover, digital images are highly preferred by people nowadays. In order to establish a secure transferring or exchange of data, the digital data needs to be secured. There are different techniques and algorithms that can used to provide security to the digital data. In this research work, a hybrid digital image security technique is proposed by combining two different types of methods and algorithms, which are used to protect the digital image. The proposed combination of steganography and asymmetric cryptography techniques are utilized to secure the digital images. © 2023 IEEE.

关键词： Cryptography

来源：评论

学校读者我要写书评

暂无评论

Accurate Classroom Person Detection Based on Multi-Frame Feature Fusion with Attention 8

Accurate Classroom Person Detection Based on Multi-Frame Fea...

引用

8th International Conference on Image, Vision and Computing, ICIVC 2023

作者： Cheng, Guoan Ren, Jiandong Li, Yuping Wang, Shengke Ding, Yougang Wang, Hao School of Information & Electrical Engineering Qingdao Harbour Vocational & Technical College Qingdao China Qingdao Harbour Vocational & Technical College Student Work Department Qingdao China College of Computer Science and Engineering Ocean University of China Qingdao China Experimental School Affiliated to Shandong University Mathematics Teaching and Research Group Heze China

ISBN: (纸本)9798350335231

In recent years, object detection technology has developed rapidly and is widely used in the field of intelligent video monitoring, especially in the classroom scenes, where incorporating the intelligent object detection technique into the video monitoring systems for intelligent monitoring purpose has important practical significance. However, surveillance videos may encounter issues such as object occlusion, motion blur, posture changes, and video defocus, which poses great challenges to object detection in the surveillance video scenarios. Therefore, in this paper, we conduct in-depth research on human detection in classroom multi camera surveillance video scenes and propose a multi frame feature fusion network based on the attention mechanism. The algorithm first adds the dilated convolution layers to the ResNet50 backbone network to expand the receptive field and retain more feature information;Secondly, a multi frame feature fusion strategy based on the attention mechanism was proposed to enhance the feature representation ability of the deep detector by fusing the feature information of adjacent frames, thereby improving the accuracy of human detection in the classroom monitoring video. To verify the effectiveness of the proposed method, we have compiled and produced a large-scale classroom monitoring video dataset, named OUC-ClassVideo. The proposed object detection network, which is developed based on the attention mechanism and multi frame feature fusion strategy, has achieved satisfactory performance on both the public dataset ImageNet VID and the OUC-ClassVideo dataset collected by ourselves. © 2023 IEEE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Yolov8-Based Deep Learning Model for Improved Drone Intrusion Detection

Yolov8-Based Deep Learning Model for Improved Drone Intrusio...

引用

Technological Advancements in Computational sciences (ICTACS), International Conference on

作者： Mohini Darji Khushi Patel Bansari Patel Krishna Thakkar Mehul Minat Meet K. Patel Computer Science & Engineering Faculty of Technology and Engineering (FTE) Devang Patel Institute of Advance Technology and Research (DEPSTAR) Charotar University of Science and Technology (CHARUSAT) Changa Gujarat India Department of Computer Science & Engineering Student of Bachelor of Technology Faculty of Technology and Engineering (FTE) Devang Patel Institute of Advance Technology and Research (DEPSTAR) Charotar University of Science and Technology (CHARUSAT) Changa Gujarat India

ISBN: (数字)9798350387490

ISBN: (纸本)9798350387506

Real-time identification of unmanned aerial vehicle (drone) is a relatively growing nascent research area which leverages on deep learning and computer vision methods. However, the question arises as to possible dangers, and misuse of drones in different circumstances. These concerns are in respect to privacy, safety and security possible violations. Cameras and software are for example bundled in detection systems where visual information is used to facilitate the detection process. Thus, This Study was devoted to examining the object detection feature of the YOLO Only Look Once (YOLOv8) algorithm and its applicability for analyzing visual material captured by drones. One of the challenges in reviewing literature was to look for an online dataset of small drones and make it publicly available. Therefore, a real-world dataset was established accurately in this study and it includes small drones. The outcome presented in the document is expected to help understand the capability of the chosen models when one attempts to recognize drones in complex conditions. Further this shall serve as base on enhancing the development of even better and long-lasting anti-drone detection systems. The mentioned issues were addressed and solved with the help of the YOLOv8 architecture implementation, and the outstanding results were obtained: the mean average precision (mAP) of $\mathbf{9 3. 9 \%}$ , the precision of $\mathbf{9 2. 9 \%}$ , and the recall of $\mathbf{9 0. 3 \%}$ .

关键词： Deep learning YOLO Visualization Software algorithms Software Safety Security Drones Videos Testing

来源：评论

学校读者我要写书评

暂无评论

Feature Extraction, Essential Dimension Estimation and Dimension Reduction Method of Colony Images

IAENG International Journal of Computer Science

引用

IAENG International Journal of computer science 2021年第2期48卷 1-13页

作者： Sun, Wei-Zhong Guo, Fu-Jun Wang, Jie-Sheng Chen, Lin Wei, Dong Du, Xin-Feng A lecturer of School of Computer Science and Software Engineering University of Science and Technology Liaoning Anshan114051 China A postgraduate student of School of Electronic and Information Engineering University of Science and Technology Liaoning Anshan114051 China A professor of School of Electronic and Information Engineering University of Science and Technology Liaoning Anshan114051 China An associate professor of School of Electronic and Information Engineering University of Science and Technology Liaoning Anshan114051 China

A colony is a group of microorganisms produced by the growth and reproduction of a single microorganism species. A method of colony image feature extraction, essential dimension estimation and dimension reduction based on digital image processing technology was proposed. Firstly, based on the HSI image color moments (first, second and third order moments), nine color characteristics of the colony images were extracted. Based on gray-level co-occurrence matrix (GLCM), twenty texture features of colony images were obtained. Then, three essential dimension estimation methods, namely, the correlation dimension estimator, the maximum likelihood estimator and the packing numbers estimator, are used to estimate the dimension of the inner low-dimensional structure of the high-dimensional data of the colony images. The results of different dimension estimators were combined with six different dimension reduction techniques (PCA, LDA, MDS, ISOMAP, SNE and NCA) respectively to form 18 different data dimension reduction methods. Based on the distance criterion function, an optimal dimension reduction method for the high-dimensional feature data of the colony images corresponding to the maximum distance criterion function was obtained. © 2021. All Rights Reserved.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Bi-Directional Conversion Algorithm of Database Based on Artificial Intelligence

Bi-Directional Conversion Algorithm of Database Based on Art...

引用

Data science and Information System (ICDSIS), IEEE International Conference on

作者： Ning Tao Lin Geng Chong Xu School of Computer Science and Engineering Shenyang Jianzhu University Shenyang Liaoning China Lin Geng Department of Student Affairs Shenyang Jianzhu University Shenyang Liaoning China

ISBN: (数字)9798350381665

ISBN: (纸本)9798350381672

The traditional database conversion algorithm is difficult to implement, expensive and difficult to popularize. The lack of conversion algorithm directly affects the result of data integration. The core problem of the mutual transformation between XML(eXtensible Markup Language) and relational data is how to construct the mapping between relational database and XML document, that is, the mapping between objects and relationships. In this paper, the element tree is used to transform the probabilistic relational data model and the probabilistic XML data model in heterogeneous databases. First, the corresponding relationship between the element tree and the unit nodes and various data models is established. Then, on this basis, the bidirectional transformation of the data model is realized through the mapping relationship between the element tree and the data. When the transaction sending frequency is 400 transactions $/ \mathrm{s}$, the write throughput is 89TPS and the query throughput is 185TPS. The query and write performance of the database bidirectional conversion algorithm based on artificial intelligence is better.

关键词： Databases XML Information sharing Transforms Relational databases Probabilistic logic Throughput

来源：评论

学校读者我要写书评

暂无评论

Artificial intelligence in the detection and classification of dental caries

引用

Journal of Prosthetic Dentistry 2025年第5期133卷 1326-1332页

作者： Ahmed, Walaa Magdy Azhari, Amr Ahmed Fawaz, Khaled Ahmed Ahmed, Hani M. Alsadah, Zainab M. Majumdar, Aritra Carvalho, Ricardo Marins Assistant Professor Department of Restorative Dentistry Faculty of Dentistry King Abdulaziz University Jeddah Saudi Arabia Associate Professor Department of Orthopedic Surgery Faculty of Medicine Cairo University Cairo Egypt Assistant Professor Department of Civil Engineering Faculty of Engineering King Abdulaziz University Jeddah Saudi Arabia Consultant in Restorative Dentistry Dental Department East Jeddah General Hospital Ministry of Health Jeddah Saudi Arabia Graduate student Department of Computer Science Computer Science and Applications Virginia Polytechnic Institute and State University Blacksburg VA United States Professor Department of Oral Biological and Medical Sciences Faculty of Dentistry University of British Columbia Vancouver BC Canada

Statement of problem: Automated detection of dental caries could enhance early detection, save clinician time, and enrich treatment decisions. However, a reliable system is lacking. Purpose: The purpose of this study was to train a deep learning model and to assess its ability to detect and classify dental caries. Material and methods: Bitewings radiographs with a 1876×1402-pixel resolution were collected, segmented, and anonymized with a radiographic image analysis software program and were identified and classified according to the modified King Abdulaziz University (KAU) classification for dental caries. The method was based on supervised learning algorithms trained on semantic segmentation tasks. Results: The mean score for the intersection-over-union of the model was 0.55 for proximal carious lesions on a 5-category segmentation assignment and a mean F1 score of 0.535 using 554 training samples. Conclusions: The study validated the high potential for developing an accurate caries detection model that will expedite caries identification, assess clinician decision-making, and improve the quality of patient care. © 2025 Editorial Council for The Journal of Prosthetic Dentistry

关键词：

来源：评论

学校读者我要写书评

暂无评论

Monitoring patients suffering from restless leg syndrome (RLS) using IoT

Monitoring patients suffering from restless leg syndrome (RL...

引用

International Conference on Control, Instrumentation, and Automation

作者： Ali Sioofi Maral Samimi Mehrshad Khosravi Armin Niakousari Ali Akbar Safavi Student research committee Shiraz University of Medical Science Shiraz Iran School of Electrical and Computer Engineering Shiraz University Shiraz Iran

Restless legs syndrome is a common neurological disorder that is often not diagnosed. It causes unusual symptoms that usually happen in the evening and at night. This can lead to problems with sleep and daily activities. It presents in different ways and can be more serious for certain groups of patients. It is important to accurately diagnose and treat this disorder. It can be difficult to figure out if someone has restless legs syndrome, especially kids and old people. Therefore, this study aims to present a tool for monitoring abnormal movements related to restless leg syndrome. An IOT-based platform with “ESP32” board and “MPU6050” module with the “Online Web server” method are used to monitor the movements. The designed platform accurately detects any vibrations and movements associated with this syndrome without any wired or complicated hardware connected to the person. This IOT based online monitoring system proved effective and can be used for long-term monitoring.

关键词：

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：