检索结果-内蒙古大学图书馆

Efficient reversible data hiding in encrypted images using Block Complexity and most significant bit inversion strategy

引用

Multimedia Tools and Applications 2024年 1-26页

作者： Yang, Cheng-Hsing Weng, Chi-Yao Hung, Chia-Ling WANG, Shiuh-Jeng Department of Computer Science and Artificial Intelligence National Pingtung University Pingtung900 Taiwan Department of Computer Science and Information Engineering National Chiayi University Chiayi600 Taiwan Department of Information Management Central Police University Taoyuan City333 Taiwan

Reversible data hiding in the encrypted images (RDHEI) has attracted more attention because RDHEI can be used for both information protection and image encryption. Many researches based on RDHEI have been proposed by using the Most Significant Bit (MSB) inversion to embed confidential information, but they might subject to errors when extracting the hidden information. This paper improves the approach based on MSB inversion and proposes a new RDHEI technique. Our approach hides the block’s position of the block in the image, which would cause misinterpretation in the original image, and then encrypts the image. The MSB inversion strategy is applied to embed the secret messages in the encrypted image. Since the location information of the error block is pre-hidden in the image, this information ensures that the secret message is correctly extracted and the image is fully recovered. We also created a multi-regular block complexity formula to determine the secret bits hidden in a block and recover the original block. In addition, we extended the design of four methods to cover various segmentation strategies and complexity calculation methods. According to the experimental results, our method can successfully extract the secret message and recover the original image intact after the encrypted image is embedded with the secret message. Generally, in using different image size, we averagely achieve the PSNR and embedding capacity of 39 experimental images at 40.633 dB and 46,298.46 bits, respectively. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Block Complexity Image Encryption MSB inversion Reversible Data Hiding

来源：评论

学校读者我要写书评

暂无评论

Comparative Analysis of various Deep learning techniques for Plant leaf disease detection: A practical approach 11

Comparative Analysis of various Deep learning techniques for...

引用

11th International Conference on Internet of Everything, Microwave engineering, Communication and Networks, IEMECON 2023

作者： Chauhan, Kapil Devi, G. Uma University of Engineering and Management Department of Computer Science & Engineering Jaipur India

ISBN: (纸本)9781665475129

Early detection and identification of plant diseases are still exceedingly difficult to do in the agriculture industry, despite their importance. We can efficiently accomplish this goal with the aid of Deep learning, an application of AI. In this study, the dataset contains 2310 images for the analysis and disease detection. For the diagnosis purpose, the ResNet 152V2, YOLO V3, and YOLO V5 were implemented on dataset. The whole image samples are further categorized into 3 major categories sets such as test, train, and validation. The images were preprocessed in the context of their identical size [224,224] for better feature selection process. After implementing the ResNet 152V2, YOLO V3, and YOLO V5 models, it can be seen that ResNet152V2 produces 26.13% Train-loss, 3S.22% Vald-loss, 93.54%, and S9.62% train-Acc and Vald-Acc respectively. Through YOLOV3, 21.20%, 96.41% was Train-loss and Vald-loss and 4S.S6%, 93.40% training and Vald-Acc was achieved. At the end of the YOLO V5 achieved higher accuracy (training and validation) i.e. 96.46%, 95.28% respectively and lesser the losses (Training and Validation) i.e. 19.57%, 19.00% respectively. © 2023 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Deep Learning Classifier to Recommend the Tourist Attraction in Smart Cities 2

Deep Learning Classifier to Recommend the Tourist Attraction...

引用

2nd International Conference on Disruptive Technologies, ICDT 2024

作者： Gupta, Keshav Kumar, Vikas Jain, Abhishek Singh, Pranita Jain, Amit Kumar Prasad, M.S.R. Grd Institute of Management and Technology Department of Computer Science and Engineering Dehradun India School of Computer Science & Engineering Dev Bhoomi Uttrakhand University Dehradun India Uttaranchal University Department of Computer Science and Engineering Dehradun India Roorkee Institute of Technology Department of Computer Science and Engineering Roorkee India Koneru Lakshmaiah Education Foundation Department of Computer Science and Engineering Vaddeswaram India

ISBN: (纸本)9798350371055

Provide an attraction recommendation system that uses deep learning and is powered by the Internet of Things (IoT) to develop the smart city visitor experience. Users of a smart city app or website will be able to record information about their trips, including whether they are going independently or with an accompanying companion, the sort of companion (e.g., a family with children or a lover), the purpose of their trip (business or pleasure), and personal characteristics (e.g., age, interests, etc.). Using this unique combination of input data, the suggested deep learning-based recommendations system would suggest tourist activities and sights that match the user's profile nicely. In addition, the suggested tourist attraction recommendations system uses actual data obtained from Internet of Things (IoT) devices to offer content-based information (such as previously looked-at sights) and context related data (such as weather conditions, location, time of day, etc.) to potential visitors in the smart city. Regarding the initial case [(a) planning and searching for activities earlier travelling], the suggested multi-label deep learning classifiers achieve a recall, accuracy, precision, and loss of 1.6%, 98.6%, 98.8%, and 98.7%, respectively, compared to other models such as extra tree, decision tree, k-nearest neighbour, and randomized forest. As for the second scenario, it can effectively suggest tourist spots while searching for smart city activities (b) with a recall, accuracy, precision, and loss of 2.6%, 98.4%, 98.6%, and 98.7%, respectively. © 2024 IEEE.

关键词： Deep Learning Internet of Things Personal Characteristics Recommendation System Smart City Activities

来源：评论

学校读者我要写书评

暂无评论

Integrated Crowd Counting System Utilizing IoT Sensors, OpenCV and YOLO Models for Accurate People Density Estimation in Real-Time Environments 1

Integrated Crowd Counting System Utilizing IoT Sensors, Open...

引用

1st International Conference on Cognitive, Green and Ubiquitous Computing, IC-CGU 2024

作者： Jayasingh, Suvendra Kumar Naik, Pintu Swain, Satyaprakash Patra, Kumar Janardan Kabat, Manas Ranjan Institute of Management and Information Technology BPUT Department of Computer Science and Engineering Odisha Cuttack India Indian Institute of Technology Department of Computer Science and Engineering Jammu India

ISBN: (纸本)9798350361780

Real-time crowd monitoring plays a pivotal role in effectively managing public spaces and ensuring safety. This study investigates the fusion of IoT devices and the YOLO object detection model to accurately count crowds. IoT devices facilitate the instantaneous collection of data from cameras, while the YOLO model adeptly identifies individuals within recorded video frames. The study rigorously assesses the performance of three YOLO variants: YOLO V5, YOLO V8 and YOLO V8 NAS. Findings reveal that YOLO V8 NAS surpasses YOLO V5 and YOLO V8 in mean average precision (mAP), achieving an exceptional mAP of 95.1%. This heightened precision is attributed to the integration of Neural Architecture Search (NAS) into the YOLO V8 NAS model, fine-tuning its architecture specifically for crowd counting tasks. It analyzes various networking models proposed in earlier studies for analyzing crowded scenes in public spaces. It emphasizes the potential of a hybrid model involving an IP camera module and a Deep Neural Network for effective crowd sensing. In this setup, the IP camera captures video footage, while the DNN detects individuals and assesses crowd density based on the count of people recognized. This approach presents an encouraging solution for real-time crowd monitoring and management in public environments. © 2024 IEEE.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Implementing a Flexible IIoT Service Framework with Microservices: A Case Study of Machine Tools 4

Implementing a Flexible IIoT Service Framework with Microser...

引用

4th IEEE International Conference on Electronic Communications, Internet of Things and Big Data, ICEIB 2024

作者： Chen, Wen-Ching Ji, Bo-Yu Chen, Hung-Hsiang Wang, Guan-Bo Li, Chin-Kuei Providence University Department of Computer Science and Communication Engineering Taichung Taiwan Providence University Department of Computer Science and Information Management Taichung Taiwan

ISBN: (纸本)9798350360721

With the continuous attention given to 'smart manufacturing' and 'smart factories,' the importance of equipment networking and data collection has been increasing. One key issue is the standardization of equipment networking. Currently, Modbus and OPC/UA are important communication protocols in machine networking. However, software engineers who mainly focus on developing user interfaces and business logic are not proficient in dealing with communication protocols. Therefore, it becomes crucial to enable IT application software engineers to easily interface with various OPC/UA and Modbus machines. Due to the requirements of integration and application of various PLC devices in the machine tool industry, we designed an efficient and flexible IIoT Gateway framework. With the assistance of the IIoT Gateway, IT application engineers developing the ERP/MES systems can easily exchange data (with read and write operations) with various PLC machines. Additionally, to meet the requirements of high performance, the system's functional modules have been designed using multi-threading, asynchronous, and non-blocking techniques. To achieve flexibility in functionality expansion, deployment, high reusing, and low coupling of modules, the Spring Cloud framework has been used to implement microservices and API design for the functional modules. In the future, various system data exchanging and visualization can be facilitated through technologies such as Micrometer/Prometheus, MQTT/Node-RED, and others for convenient logging and tracking. © 2024 IEEE.

关键词： Application programs

来源：评论

学校读者我要写书评

暂无评论

Detection of communicable and non-communicable diseases using hyperparameter optimization with Bi-LSTM model in pathology images

引用

International Journal of Intelligent Computing and Cybernetics 2023年第4期16卷 649-664页

作者： Shiva Sumanth Reddy C.Nandini Department of Computer Science and Engineering Dayananda Sagar Academy of Technology and ManagementBangaloreIndia Dayananda Sagar Academy of Technology and Management BangaloreIndia

Purpose:The present research work is carried out for determining haemoprotozoan diseases in cattle and breast cancer diseases in humans at early *** combination of LeNet and bidirectional long short-term memory(Bi-LSTM)model is used for the classification of heamoprotazoan samples into three classes such as theileriosis,babesiosis and ***,BreaKHis dataset image samples are classified into two major classes as malignant and *** hyperparameter optimization is used for selecting the prominent *** main objective of this approach is to overcome the manual identification and classification of samples into different haemoprotozoan diseases in *** traditional laboratory approach of identification is time-consuming and requires human *** proposed methodology will help to identify and classify the heamoprotozoan disease in early stage without much of human ***/methodology/approach:LeNet-based Bi-LSTM model is used for the classification of pathology images into babesiosis,anaplasmosis,theileriosis and breast images classified into malignant or *** optimization-based super pixel clustering algorithm is used for segmentation once the normalization of histopathology images is *** edge information in the normalized images is considered for identifying the irregular shape regions of images,which are structurally ***,it is compared with another segmentationapproach circularHough Transform(CHT).The CHT is used toseparatethe *** Canny edge detection and gaussian filter is used for extracting the edges before sending to ***:The existing methods such as artificial neural network(ANN),convolution neural network(CNN),recurrent neural network(RNN),LSTM and Bi-LSTM model have been compared with the proposed hyperparameter optimization approach with LeNET and *** results obtained by the proposed hyperparameter optimization-Bi-LSTM model showed the accuracy of

关键词： Breast cancer detection Convolution neural network Deep neural network Haemoprotozoan disease detection Hyper-parameter optimization LeNet Bi-LSTM

来源：评论

学校读者我要写书评

暂无评论

UPB Scientific Bulletin, Series C: Electrical Engineering an...

引用

UPB Scientific Bulletin, Series C: Electrical engineering and computer science 2024年第1期86卷 91-104页

作者： Xu, Yong Peng, Yunke Wang, Hengna Wang, Xue’Er Department of Computer Science & Technology Anhui University of Finance & Economics Bengbu233000 China School of Management Science & Engineering Anhui University of Finance & Economics Bengbu233000 China

In addressing the limitations of traditional short text similarity calculation methods, this paper presents SMSABLC, a deep learning-based approach that takes into account polysemy, character order, and contextual semantics. Utilizing word embedding, SMSABLC converts short text into vectors, initiating the integration of a multi-head self-attention mechanism. This mechanism adeptly captures the relationship between words and the overall context within the short texts, spanning across multiple subspaces. Additionally, two opposing LSTM models are employed to acquire bidirectional sequential information from the character context in the short texts. Employing a combination of a convolutional layer and a pooling layer, CNN effectively facilitates the extraction of local character features inherent in the short text. Moving forward, the subsequent step entails the computation of the discernible difference existing between the two distinct short text vectors. This difference value is then inputted into a fully connected layer, whereupon the ensuing utilization of the Sigmoid function aids in the determination of the extent of similarity between the two textual entities. This article conducted experiments on two datasets, CCKS2018 and LCQMC, and compared with traditional methods and some deep learning based methods, SMSABLC achieved better experimental results. Through the analysis of experimental results, it can be concluded that SMSABLC achieves significant improvements in the calculation of short text similarity by effectively incorporating a wide range of deep semantic information. © 2024, Politechnica University of Bucharest. All rights reserved.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Recommendation Systems in Education 7

Recommendation Systems in Education

引用

7th International Conference on Electronics, Materials engineering and Nano-Technology, IEMENTech 2023

作者： Dutta, Anwesha Patwari, Sruti Mondal, Anupam University of Engineering & Management Institute of Engineering & ManagementKolkata Department of Computer Science and Engineering Kolkata India

ISBN: (纸本)9798350305517

In the dynamic landscape of online education, the quest for effective course discovery is a multifaceted challenge. This paper investigates a recommendation system tailored to enrich course discovery on Udemy, employing a context-based, collaborative, and hybrid approach. Our system excels with a multi-dimensional course recommendation strategy, seamlessly blending three core techniques: context-based recommendations that consider user profiles and learning contexts, collaborative filtering to identify behavioral patterns and hybridization for fine-tuned suggestions aligned with immediate learning needs and user community insights. The paper delves into evaluating recommendation systems using appropriate metrics and benchmark datasets, addressing challenges like limited data and initiation hurdles with practical solutions. Looking forward, we explore the potential of emerging technologies, including deep learning and reinforcement learning, to further enhance recommendation algorithms. Our vision prioritizes personalization, diversity, and transparency, shaping the future of course recommendations on Udemy. © 2023 IEEE.

关键词： Recommender systems

来源：评论

学校读者我要写书评

暂无评论

Architectural Visualization using Augmented Reality 3

Architectural Visualization using Augmented Reality

引用

3rd International Conference on Intelligent and Innovative Technologies in Computing, Electrical and Electronics, IITCEE 2025

作者： Raj, Nikhil Menon, Hema P. Satheesh, Abhinand Naveen Nikhil, A.P. Vishnuraj, K.R. Sreepathy Institute of Management and Technology Department of Computer Science and Engineering Vavannor Kerala Palakkad India

ISBN: (纸本)9798331515911

In the dynamic field of architectural design, effective communication stands as a requirement for successful project realization. However, traditional 2D methods often struggle to convey the depth and essence of architectural visions to stakeholders. Augmented Reality (AR) emerges as a revolutionary tool, poised to transform architectural communication and stakeholder engagement. This work is an exploration of the transformative power of Augmented Reality in architectural design communication, employing a comprehensive methodology. By leveraging state-of-the-art technological innovations, the aim is to provide architects and designers with groundbreaking tools to translate their blueprints into immersive, dynamic experiences. Beginning with collaborative requirement analysis, conceptual design, and data acquisition, the optimization of assets for AR rendering follows suit. Augmented Reality, in tandem with Unity 3D, Figma, and specifically smartphones as AR devices are used for realization of the work. This integration fosters collaborative, immersive design experiences and propels architectural discourse into a new era of interactive visualization and communication. © 2025 IEEE.

关键词： Conceptual design

来源：评论

学校读者我要写书评

暂无评论

Analysis of community question-answering issues via machine learning and deep learning:State-of-the-art review

引用

CAAI Transactions on Intelligence Technology 2023年第1期8卷 95-117页

作者： Pradeep Kumar Roy Sunil Saumya Jyoti Prakash Singh Snehasish Banerjee Adnan Gutub Department of Computer Science and Engineering Indian Institute of Information TechnologySuratIndia Indian Institute of Information Technology DharwadIndia Department of Computer Science and Engineering National Institute of TechnologyPatnaIndia The York Management School University of YorkYorkUK Computer Engineering Department College of Computer&Information SystemsUmm Al-Qura UniversityMakkahSaudi Arabia

Over the last couple of decades,community question-answering sites(CQAs)have been a topic of much academic *** have often leveraged traditional machine learning(ML)and deep learning(DL)to explore the ever-growing volume of content that CQAs *** clarify the current state of the CQA literature that has used ML and DL,this paper reports a systematic literature *** goal is to summarise and synthesise the major themes of CQA research related to(i)questions,(ii)answers and(iii)*** final review included 133 *** research themes include question quality,answer quality,and expert *** terms of dataset,some of the most widely studied platforms include Yahoo!Answers,Stack Exchange and Stack *** scope of most articles was confined to just one platform with few cross-platform *** with ML outnumber those with ***,the use of DL in CQA research is on an upward trajectory.A number of research directions are proposed.

关键词： answer quality community question answering deep learning expert user machine learning question quality

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：