检索结果-内蒙古大学图书馆

Deep Neural Network and GAN-Based Reversible Data Hiding in Encrypted Images: A Privacy-Preserving Approach

SN computer Science 2024年第1期5卷 45页

作者： Nalavade, Jagannath E. Patil, Akshta Buchade, Amar Jadhav, Nagesh Department of Computer Science and Engineering MIT Art Design and Technology University School of Computing Pune India Department of Computer Engineering Rajarambapu Institute of Technology Sakharale Sangli India

In light of recent incidents involving the leakage of private photographs of Hollywood celebrities from iCloud, the need for robust methods to safeguard image content has gained paramount importance. This paper addresses this concern by introducing a novel framework for reversible image editing (RIT) supported by reversible data hiding with encrypted images (RDH-EI) techniques. Unlike traditional approaches vulnerable to hacking, this framework ensures both efficient and secure data embedding while maintaining the original image’s privacy. The framework leverages two established methods: secret writing and knowledge activity. While secret writing is susceptible to hacking due to the complex nature of cipher languages, RDH-EI-supported RIT adopts a more secure approach. It replaces the linguistic content of the original image with the semantics of a different image, rendering the encrypted image visually indistinguishable from a plaintext image. This novel substitution prevents cloud servers from detecting encrypted data, enabling the adoption of reversible data hiding (RDH) methods designed for plaintext images. The proposed framework offers several distinct advantages. Firstly, it ensures the confidentiality of sensitive information by concealing the linguistic content of the original image. Secondly, it supports reversible image editing, enabling the restoration of the original image from the encrypted version without any loss of data. Lastly, the integration of RDH techniques designed for plaintext images empowers the cloud server to embed supplementary data while preserving image quality. Incorporating convolutional neural network (CNN) and generative adversarial network (GAN) models, the framework ensures accurate data extraction and high-quality image restoration. The applications of this concealed knowledge are vast, spanning law enforcement, medical data privacy, and military communication. By addressing limitations of previous methods, it opens new avenues

关键词： Deep hiding Deep neural network GAN model Reversible data hiding (RDH)

来源：评论

学校读者我要写书评

暂无评论

3D Human Pose Estimation Using Two-Stream Architecture with Joint Training

引用

computer Modeling in engineering & Sciences 2023年第10期137卷 607-629页

作者： Jian Kang Wanshu Fan Yijing Li Rui Liu Dongsheng Zhou National and Local Joint Engineering Laboratory of Computer Aided Design School of Software EngineeringDalian UniversityDalian116622China Dalian Maritime University Dalian116023China

With the advancement of image sensing technology, estimating 3Dhuman pose frommonocular video has becomea hot research topic in computer vision. 3D human pose estimation is an essential prerequisite for subsequentaction analysis and understanding. It empowers a wide spectrum of potential applications in various areas, suchas intelligent transportation, human-computer interaction, and medical rehabilitation. Currently, some methodsfor 3D human pose estimation in monocular video employ temporal convolutional network (TCN) to extractinter-frame feature relationships, but the majority of them suffer from insufficient inter-frame feature relationshipextractions. In this paper, we decompose the 3D joint location regression into the bone direction and length, wepropose the TCG, a temporal convolutional network incorporating Gaussian error linear units (GELU), to solvebone direction. It enablesmore inter-frame features to be captured andmakes the utmost of the feature relationshipsbetween data. Furthermore, we adopt kinematic structural information to solve bone length enhancing the use ofintra-frame joint features. Finally, we design a loss function for joint training of the bone direction estimationnetwork with the bone length estimation network. The proposed method has extensively experimented on thepublic benchmark dataset Human3.6M. Both quantitative and qualitative experimental results showed that theproposed method can achieve more accurate 3D human pose estimations.

关键词： 3D human pose improved TCN GELU kinematic structure

来源：评论

学校读者我要写书评

暂无评论

A comprehensive review of effective parameters to improve the performance of the Savonius turbine using a computational model and comparison with practical results

引用

Water-Energy Nexus 2024年第1期7卷 266-274页

作者： Jebelli, Ali Lotfi, Nafiseh Saeid Zare, Mohammad Yagoub, Mustapha C.E. Department of Engineering and Design Robotic Century Inc Alberta Canada Faculty of New Science and Technologies Tehran University Tehran Iran School of Electrical Engineering and Computer Science University of Ottawa ON Canada

Amidst growing global concerns over climate change and escalating greenhouse gas emissions from fossil fuels, the pursuit of renewable energy sources has become critical. This study focuses on harnessing hydropower using Savonius turbines, which are known for their efficiency in generating energy at lower flow rates. However, the intrinsic low efficiency of these turbines necessitates precise optimization tailored to specific river or channel conditions. In this research, we optimized the performance of Savonius turbines by analyzing key parameters such as the height-to-diameter ratio, blade twist, and the integration of multi-stage configurations with deflectors. Our findings reveal significant efficiency improvements through strategic modifications. Specifically, by reducing the height-to-diameter ratio from 1.2 to 0.8 and maintaining a Tip Speed Ratio (TSR) of 0.6, the power coefficient increased by 15%, from 0.33 to 0.38. Further optimization was achieved by adjusting the blade twist angle, with an increase in power coefficient up to an optimal angle of 45°, beyond which efficiency declined. Implementing a two-stage turbine setup with a 90-degree phase difference between stages further improved the power coefficient to 0.51 at the same TSR. Additionally, the use of deflectors, particularly at a 90° angle, significantly boosted the power coefficient, highlighting their effectiveness in optimizing water flow impact on the turbine. This comprehensive study not only advances the understanding of Savonius turbine optimization but also contributes to broader renewable energy applications. The research offers critical insights into sustainable hydroelectric power generation, providing practical solutions to enhance turbine performance for real-world applications. © 2024

关键词： Clean energy

来源：评论

学校读者我要写书评

暂无评论

SLAM Loop Closure Detection Algorithm Based on 3D Bag-of-Words Model

SLAM Loop Closure Detection Algorithm Based on 3D Bag-of-Wor...

引用

2023 International Conference on computer, Internet of Things and Smart City, CIOTSC 2023

作者： Liangdong, Wu Yaping, Zou Dong, Wang Ling, Chen Hunan Normal University School of Computer Engineering and Design Changsha China

ISBN: (纸本)9798350306569

In outdoor environments, the loop closure detection in laser-based SLAM faces challenges such as complex lighting variations, low-texture regions, occlusions, and dynamic objects, which limit the accuracy and efficiency of loop closure detection. To address this issue, a novel laser-based SLAM loop closure detection algorithm is proposed, specifically designed for outdoor environments, based on three-dimensional global descriptor features. The algorithm utilizes a BoW3D model constructed from the three-dimensional laser features for precise point-to-point matching and loop closure detection. The proposed algorithm is integrated into the LeGO-LOAM system and evaluated on the publicly available KITTI dataset. Experimental results demonstrate a 64% improvement in absolute trajectory accuracy and reduced computational time compared to the baseline algorithm. © 2023 IEEE.

关键词： 3D modeling

来源：评论

学校读者我要写书评

暂无评论

Sybil Assault Detection in VANET with Efficient Network Analysis

Sybil Assault Detection in VANET with Efficient Network Anal...

引用

2024 MIT Art, design and Technology school of Computing International Conference, MITADTSoCiCon 2024

作者： Mukherjee Mathur, Shubhra Jadhav, Nagesh Gupta, Ravindra Design and Technology University Pune Sarvepalli Radakrishnan University School of Computing MIT Art Department of Computer Science and Engineering Bhopal India Design and Technology University School of Computing MIT Art Department of Computer Science and Engineering Pune India Sarvepalli Radakrishnan University School of Computing Department of Computer Science and Engineering Bhopal India

ISBN: (纸本)9798350362879

A developing technology that can be highly helpful for both intelligent transportation services and safety and security is the Automobile ad hoc network, or VANET. Nevertheless because of the great mobility and wireless connection of cars, there are numerous security risks that jeopardize people's safety and security when driving. The Sybil assault, in which the perpetrator makes up a false identity to obtain significant influence within the network and delay certain services and manipulate others by fictitious voting, is one of the main security issues. People can avoid being duped by an attacker or falling into traps when attacks are detected early. This study describes two methods for detecting Sybil attacks: the first uses the Poisson Distribution Method in order to forecast traffic on the street, whereas the latter examines network efficiency for packet delivery ratio (PDR) in both benign additionally malicious environments. According to the simulation's findings, PDR lowers the number of fictitious cars in the network. Our method is straightforward and efficient because it doesn't involve a lot of computational overhead and doesn't breach users' privacy concerns. © 2024 IEEE.

关键词： Poisson distribution

来源：评论

学校读者我要写书评

暂无评论

Stationary wavelet transform and SpinalNet trained light spectrum Tasmanian devil optimization enabled DR detection using fundus images

引用

Multimedia Tools and Applications 2025年第4期84卷 1597-1626页

作者： Tamboli, Mubin Shoukat Dhumane, Amol Prasad, Rajesh Prasad, Jayashree Rajesh Ranjan, Nihar M. Computer Engineering Pimpri Chinchwad College of Engineering Pradhikaran Maharashtra Pune411044 India Computer Science and Engineering Symbiosis Institute of Technology Maharashtra Pune India Computer Science and Engineering School of Computing MIT Art Design and Technology University Loni Kalbhor Maharashtra Pune412201 India Information Technology JSPM’s Rajarshi Shahu College of Engineering Tathawade Maharashtra Pune411033 India

Diabetes is a common disease that causes complications in the eyes known as Diabetic Retinopathy (DR). It aids in discovering the DR and tends to be the main cause behind people’s blindness amidst the previous decades. For prevent the complications of DR and to control the level of blood Glucose, the timely and crucial diagnosis is essential. A model is provided for detecting the DR. Here, Light Spectrum Tasmanian Devil Optimization (LSTDO) is utilized with SpinalNet for DR detection. The method undergoes an adaptive median filter and Region of interest mining process to generate a pre-processed image. The Sparse Fuzzy C-Means (FCM) is adapted for segmenting the optic disks followed by feature extraction. Then, the Hough line transformation with Tyler Coye algorithm (HLTCA) is used for blood vessel segmentation. Concurrently, the Stationary Wavelet Transform (SWT) is adapted to input image to overwhelm the deficiency of translation-invariance issue and then the feature mining is done. The feature vector is generated by unifying the outputs of the three-feature extraction phases and is employed to detect DR. The accuracy, sensitivity, and specificity obtained by the LSTDO-based SpinalNet are 91.6%, 89.9% and 92.1%, respectively. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2024.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Evaluation of Consumer Behavior Regarding Food Delivery Applications in India 4

Evaluation of Consumer Behavior Regarding Food Delivery Appl...

引用

4th International Conference on Innovative Practices in Technology and Management, ICIPTM 2024

作者： Titus, Ray Babu, Tina Nair, Rekha R Sharma R, Rajesh Chinnaiyan, R. Sungheetha, Akey Alliance University Bengaluru India Alliance University Alliance School of Engineering and Design Department of Computer Science and Engineering Bengaluru India

ISBN: (纸本)9798350307757

This article investigates customer behaviour towards meal delivery apps, focusing on factors such as restaurant diversity, food packaging quality, application design, and user interface. According to the study, having a varied choice of eateries increases consumer happiness, which leads to more app usage. However, the quality of food packaging has no meaningful impact on overall satisfaction. Fortunately the study emphasises the importance of application design and user interface in influencing consumer behaviour. Both factors have a substantial impact on overall happiness, with user-friendly interfaces attracting new users and encouraging frequent app usage. The findings highlight the necessity of organisations addressing these characteristics in order to improve customer satisfaction, increase app engagement, and create long-term client loyalty. Understanding and adapting to client preferences in these areas can help food delivery applications compete successfully. © 2024 IEEE.

关键词： Consumer behavior

来源：评论

学校读者我要写书评

暂无评论

A Self-adaptive Digital Twin with Broad Learning System: An Example of Heat Pump

A Self-adaptive Digital Twin with Broad Learning System: An ...

引用

2024 IEEE PES Innovative Smart Grid Technologies Europe Conference, ISGT EUROPE 2024

作者： Fu, Kun Song, Ruihao Pant, Prashant Hamacher, Thomas Peric, Vedran Technical University of Munich School of Engineering and Design Garching Germany Aarhus University Department of Electrical and Computer Engineering Aarhus Denmark

ISBN: (纸本)9789531842976

This paper introduces a novel self-adaptive digital twin (DT) based on broad learning system (BLS), which has potential to be evolved in the power and energy sectors. Traditional data-driven DT approaches in these sectors struggle with the requirement for extensive historical data and flexibility in adapting to changes in operating conditions. By integrating BLS, our method notably decreases the volume of initial training data required and improves the system's ability to adjust to new conditions uncovered in initial training data. As an example, the proposed method is applied on a 5 kW air-source heat pump system. Finally, the effectiveness of the proposed method is demonstrated through comparison with a benchmark model calibrated with experimental data. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Unveiling Consumer Online Reviews: An In-Depth Analysis of Uses and Gratificatications 4

Unveiling Consumer Online Reviews: An In-Depth Analysis of U...

引用

4th International Conference on Innovative Practices in Technology and Management, ICIPTM 2024

作者： Titus, Ray Rajesh Sharma, R. Chinnaiyan, R. Sungheetha, Akey Babu, Tina Nair, Rekha R Alliance University Bengaluru India Alliance University Alliance School of Engineering and Design Department of Computer Science and Engineering Bengaluru India

ISBN: (纸本)9798350307757

This research scrutinizes the uses and gratifica- tions linked with consumer online reviewing, recognizing the motivations driving individuals to share feedback in digital spaces. Recognizing the constraints of time, money, and expertise, as well as potential limitations in sample selection, the study acknowledges the possibility of a small sample size hindering generalizability to the broader population of online consumers. Despite these limits, the study intends to investigate several forms of online evaluations (positive, negative, and neutral) in order to uncover the underlying motivations for customers' participation in digital mechanisms for feedback. Furthermore, the research endeavors to explore the repercussions businesses may encounter when providing incentives for customer feedback. While not considering the influence of different platforms or the specific stage of the purchasing process most affected, this study forms a foundational exploration into the multifaceted landscape of consumer online reviewing. By identifying and quantifying the components that impact consumer purchasing decisions, the research aims to shed light on the complex interplay between consumer motivations, online reviews, and business outcomes. This nuanced examination contributes to the existing body of knowledge in understanding the dynamics of online consumer behavior and provides valuable insights for businesses navigating the challenges and opportunities of the digital marketplace. © 2024 IEEE.

关键词： Motivation

来源：评论

学校读者我要写书评

暂无评论

Semantic Analysis Using Deep Learning for Predicting Stock Trends 2

Semantic Analysis Using Deep Learning for Predicting Stock T...

引用

2nd International Conference on Machine Learning and Data engineering, ICMLDE 2023

作者： Galphade, Manisha Nikam, V.B. Yedurkar, Dhanalekshmi Singh, Prabhishek Stephan, Thompson Department of Computer Science & Engineering School of Computing MIT Art Design & Technology University Pune India Department of Computer Engineering & IT Veermata Jijabai Technological Institute Mumbai India Department of Computer Science & Engineering School of Computing MIT Art Design & Technology University Pune India School of Computer Science Engineering and Technology Bennett University Greater Noida India Department of Computer Science & Engineering Graphic Era Deemed to Be University Uttarakhand Dehradun India

Company Investors and financial professionals mostly rely on quarterly reports to help them decide the ways to invest in stocks and assess the company's current performance. Quarterly company reports offer an abstracted perspective of the company's overall past performance, as well as its present situation and the market value of its market share. Financial text streams in quarterly report are unstructured naturally, but they represent cooperative expressions that are of important in any financial decision for stake holder. It will be both daunting and necessary to procedure intelligence of unstructured textual data. In this study, we address important queries related with the explosion of interest in a method to extract useful information from unstructured data and the way to work out if such insight provides any hints regarding the trends of financial markets. There is a lack of availability in the labeled dataset for financial sentiment analysis applications. The pre-trained language model employs very little labeled parameters that is used for a variety of domain specific corpora including financial sentiment analysis. In this paper, FinBERT, a model built on the BERT framework, to address linguistics challenges in the financial domain. The proposed work uses twelve transformer layers and twelve attention layers with several million parameters. The design of encoder and decoder comprises of several attention layers along with RNN. This arrangement aids to recognize instances processing the strongest relation between the words within a particular sentence. The experimentation results shows that the presented method surpass the state-of-the-art methods for financial datasets. The results are also compared with other existing models using the same financial dataset. It is observed that the FinBERT attains an accuracy of 84.77% on quarterly reports despite using a lesser training set. © 2024 Elsevier B.V.. All rights reserved.

关键词： Sentiment analysis

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：