检索结果-内蒙古大学图书馆

Deep Learning Framework for Robust Deep Fake Image Detection: A Review

Deep Learning Framework for Robust Deep Fake Image Detection...

2024 International Conference on Artificial Intelligence and Quantum Computation-Based Sensor Applications, ICAIQSA 2024

作者： Bhandarkar, Ankita Khobragade, Prashant Pawar, Raju Lokulwar, Prasad Saraf, Pranay Department of Computer Science and Engineering Nagpur India G H Raisoni College of Engineering Department of Computer Science & Engineering Nagpur India G H Raisoni College of Engineering Department of DIC Nagpur India

ISBN: (纸本)9798331517953

Deepfake technology, which uses deep learning to change pictures and videos, makes it difficult to identify and tell the real and fake images. People are worried about false information, data breaches, and bad uses of deepfake generation methods that are getting better and better very quickly. As the name suggests, this study looks at the current deep learning methods for finding deepfake pictures, focusing on their pros and cons. It looks at how well CNN method, autoencoders method, RNN method and attention-based models can discover little visual blemishes and blunders that were included amid the deepfake creation handle. The study also talks about how data addition, transfer learning, and ensemble learning can help improve the efficiency of identification. Additionally, it talks about how deepfake technology is changing and the need for flexible models that can successfully fight more complex fakes. Problems like small datasets, heavy processing needs, and the chance of hostile attacks are talked about, along with possible answers such as combining blockchain technology and real-time detection systems. This review gives an indepth look at the latest progress and gaps in deepfake detection. The goal is to help make tools that are stronger, more scalable, and more reliable to fight the growing threat of deepfake picture manipulation. © 2024 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Dual image based secured reversible data hiding scheme exploiting huffman compression tree combining bit-reversal permutation technique

引用

Multimedia Tools and Applications 2025年第9期84卷 5653-5698页

作者： Datta, Kankana Jana, Biswapati Chakraborty, Mamata Dalui Department of Computer Applications Haldia Institute of Technology HIT Campus Hatiberia Haldia Purba Medinipur West Bengal Haldia India Department of Computer Science Vidyasagar University West Bengal Midnapore India Department of Computer Science and Engineering National Institute of Technology West Bengal Durgapur India

In the area of data hiding and information security, the greater need is to ensure high embedding capacity of the stego media without hampering the visual quality while ensuring the tightest possible security. Now, it has become one of the biggest challenge to meet all these requirements. Embedding secret messages in dual images is one of the latest techniques that aims to cater such needs. However, there are very few data hiding schemes that are currently using dual images, but are suffering from several shortcomings, such as security loophole and poor visual quality with limited hiding capacity. In this paper, a dual image-based reversible data hiding scheme has been proposed where multiple bits can be embedded within a pair of pixels dynamically by Huffman compression where different pseudo codes are generated for different chunk of secret bits which are embedded by Bit-Reversal Permutation (BRP) and X-OR operations. Finally, pixels are interchanged between the dual images based on odd-even properties of the pixel values. The functional efficiency of the proposed scheme is evaluated by comparing the relevant parameters of different state-of-the-art schemes. It is established that the proposed scheme provides more than 64 dB PSNR value on average after embedding a maximum of 3, 27, 680 bits of secret data which ensures good visual quality and high embedding capacity as compared to other state-of-the-art schemes thereby benefitting innumerable applications across public and private sectors. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Pixels

来源：评论

学校读者我要写书评

暂无评论

Overnight Charging Mechanism of Battery Electric Buses for a Transit Network in Smart Cities 5

Overnight Charging Mechanism of Battery Electric Buses for a...

引用

5th Technology Innovation Management and engineering science International Conference, TIMES-iCON 2024

作者： Sobhani, Ehsan Yassine, Abdulsalam Ameli, Amir Riahinia, Shahin Department of Computer Science Lakehead University Thunder BayON Canada Department of Software Engineering Lakehead University Thunder BayON Canada Department of Electrical and Computer Engineering Lakehead University Thunder BayON Canada

ISBN: (纸本)9798350362602

—Battery electric buses (BEBs) are known for being eco-friendly transportation in smart cities. They are cost-effective compared to their diesel counterpart if BEBs are charged efficiently. There are two main charging approaches for BEBs, namely, off-service (overnight) and on-route (opportunity) charging. The overnight electricity rate is typically lower than the daytime rate. Consequently, overnight charging is considered the most affordable approach to meet the daily energy needs of the electrified transit network. This paper introduces a new intelligent overnight charging mechanism—i.e., Priority Charging Mechanism (PCM)—that charges BEBs simultaneously using the optimum number of chargers to minimize infrastructure costs. The model is evaluated using the actual transit network data of the city of Thunder Bay. ©2024 IEEE.

关键词： Charging stations

来源：评论

学校读者我要写书评

暂无评论

A Prototype Preceding Vehicle Identification System Development and Field Evaluation 10

A Prototype Preceding Vehicle Identification System Developm...

引用

10th International Conference on Vehicle Technology and Intelligent Transport Systems, VEHITS 2024

作者： Mu, Zeyu Tu, Guancheng Shi, Austin Yang, Kun Sun, Yixin Shen, Cong Park, B. Brian Department of Systems & Information Engineering University of Virginia CharlottesvilleVA United States Department of Computer Science University of Virginia CharlottesvilleVA United States Department of Electrical & Computer Engineering University of Virginia CharlottesvilleVA United States Departments of Computer Science and Electrical & Computer Engineering University of Virginia CharlottesvilleVA United States Departments of Civil & Environmental Engineering and Systems & Information Engineering University of Virginia CharlottesvilleVA United States

ISBN: (纸本)9789897587030

Preceding vehicle identification is crucial for establishing cooperative platooning. This paper presents the development of a prototype preceding vehicle identification system (PVIS) and its field evaluation for the assessment of commercial viability. We designed and assembled a prototype consisting of a processing unit (Jetson Nano board), a communication device (Wi-Fi dongle), a GPS unit, and a distance measurement sensor (Terabee sensor). The Jetson Nano integrates the SparkFun GPS-RTK-SMA unit, the Terabee time-of-flight sensor, and the Wi-Fi dongle. The PVIS prototype in the ego vehicle measures the distance to its preceding vehicle and receives the GPS data from potential preceding vehicles with the PVIS prototypes. With these, the PVIS in the ego vehicle determines the connectivity of the preceding vehicle. The field evaluation results showed that the prototype PVIS works as designed, and each successful identification takes about 5.3 seconds. However, it was found that the Terabee (time of flight) sensor, at times, did not properly measure distances, likely due to an angle issue caused by the roadway surface and vibration of the vehicle. We discussed how to overcome the challenges identified and enhance the prototype for successful commercialization. Copyright © 2024 by SCITEPRESS - science and Technology Publications, Lda.

关键词： Vehicle to vehicle communications

来源：评论

学校读者我要写书评

暂无评论

A Sustainable approach to Design and Optimize a Solar Powered E2W Charging Station for Manipal University Jaipur 3

A Sustainable approach to Design and Optimize a Solar Powere...

引用

3rd IEEE International Conference on Power Electronics, Intelligent Control and Energy Systems, ICPEICES 2024

作者： Kiran Chaurasia, Sandeep Ravishankar Kamath, H. Manipal University Jaipur Department of Electrical Engineering Jaipur India Manipal University Jaipur Department of Computer Science & Engineering Jaipur India The Assam Kaziranga University Department of Electrical Engineering Jorhat India

ISBN: (纸本)9798350387193

India witnessed 34.42 % growth of electric two-wheelers (E2W) in the third quarter of fiscal year 2024. The average solar incidence across the country ranges between 4 - 7 kWh/sq.m/day. Adoption of electric vehicles could foster India's commitment towards sustainability. Rajasthan receives the highest annual radiation energy. The state also has highest numbers of universities. Setting up a E2W charging station on the university campus will increase charging convenience, support research activities and reduce the carbon footprint. This case study constructs a self-financed 18.00kWp E2W charging station using PV Syst V7.4.3 software. The Ideal scenario projected a payback period of 6.2 years with 15620.00 USD capital investment. The levelized cost of energy (LCOE) of the E2W station is 0.05 USD which is less than the charging rate of public electric vehicle charging station across the state. © 2024 IEEE.

关键词： Charging stations

来源：评论

学校读者我要写书评

暂无评论

A Literary Survey for Blockchain Application for Supply Chain Management of Farm Produces 2

A Literary Survey for Blockchain Application for Supply Chai...

引用

2nd International Conference on Emerging Trends in Information Technology and engineering, ic-ETITE 2024

作者： Akiladevi, R. Ashok Balaji, S. Allen Shepherd, V. Rajalakshmi Engineering College Department of Computer Science and Engineering Tamil Nadu India

ISBN: (纸本)9798350328202

The size of the global blockchain market in food supply chains and agricultural activities was expected to reach USD 133 million in 2020. The growing need among stakeholders to track and trace the finished goods and raw materials is what is driving this expansion, as it builds trust among all parties involved. Because customers are growing more conscious of provenance, more players in the food industry are turning to blockchain technology. But only organized food retailers and branded corporations may benefit from blockchain applications and traceability. There is no system in place to validate data in real time, nor is there any guarantee of the standard of the raw commodities used in the food sector. However, neither producers nor customers - two groups from opposite ends of the supply chain - benefit financially from the conventional method. Labels with embedded barcodes, QR's and monitoring technologies will help farmers get paid more and promote confidence in the quality of their produce thanks to a bespoke blockchain for traceability. A model that promotes end-to-end services also bolsters the transparency in the system, and makes it easier for the parties involved to track their interests, be it the delivery or the payments. © 2024 IEEE.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

An AI Framework Model for Smart Prediction of Ripeness in Regional Fruits and Vegetables 4

An AI Framework Model for Smart Prediction of Ripeness in Re...

引用

4th International Conference on Sustainable Expert Systems, ICSES 2024

作者： Priyadharshini M., Indira Anusha, G. Padmavathy, C. Lokshana, R.J. Pavithra, V. Murugeshwari, M. Sri Ramakrishna Engineering College Department of Computer Science and Engineering Coimbatore India

ISBN: (纸本)9798331540364

It is imperative to take great measures of nutrition facts to stay away from different illnesses. The Standard admission of various nutrition facts are basic for keeping the correct equilibrium of nutrition content in the human body. In this project, a web-based application for estimating the condition of fruits/vegetables and nutrition facts of food improving individual's utilization propensities for wellness is developed. Additionally, by incorporating ripeness level estimation, the project offers a more comprehensive understanding of the life cycle and quality of fruits and vegetables, enhancing its utility and practicality. The nutrition facts portion of a fruit or vegetable is distinguished utilizing standard picture dataset utilizing various advances such as pre-processing, attribute extraction, training and categorization using shape and size with the help of machine learning techniques. Fruit or vegetable nutrition facts object dimensions are determined using image processing techniques. The final step is to estimate the nutrition facts (calories,protein,iron,calcium,potassium) in the given fruit or vegetable and provide the users, patients with optimum solutions for fruit or vegetable intake. This project is about Fruits-Vegetable classification and nutrition facts prediction. For this proposed system Convolutional Neural Network, KNN and Random Forest are employed. The CNN model achieves a higher accuracy of99.21. Hence the CNN model performs better than other models in an Integrated Approach to Fruits and Vegetables. It is a simple web application that every user can use it. User need to upload the image of any fruit or vegetable. Our system will automatically classify the Image and it will give you the prediction about the name of fruit or vegetable, and now it includes one another module which will give the nutrition facts of the predicted image. © 2024 IEEE.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Fully LTPS-TFT-Based Bi-Directional Biomedical Interface Circuit for Large-Area Healthcare Applications

IEEE Journal on Flexible Electronics

引用

IEEE Journal on Flexible Electronics 2025年第12期3卷 526-532页

作者： Zhang, Hanbo Lou, Yuqing Zhang, Zhihang Li, Yongfu Rokhan, Fakhrul Wang, Guoxing Zhao, Jian Shanghai Jiao Tong University School of Electronic Information and Electrical Engineering Shanghai200240 China Universiti Putra Malaysia Faculty of Engineering Department of Computer and Communication System Engineering Selangor Serdang43400 Malaysia

This paper proposed a fully LTPS-TFT-based bi-directional biomedical pixel interface with integrated a high linearity stimulator and a high-performance bio-potential sensing front-end circuit to amplify and digitize biological signals for high robustness data transmission. All circuits are designed and manufactured under a 3-μm LTPS process. We demonstrated the experiment in saline using the stimulator circuit to simulate stimulation inside the organism, achieving stimulation with different average currents under different duty cycles. The proposed front-end circuit has a gain of 40 dB. The referred input voltage noise of the entire signal chain is 86.2 μV/√Hz, and the ENOB is 9.13 bits at an input of 0.5 mVPP. Simultaneously conducting statistical testing on 20 chips has achieved a 1.05 dB SNDR standard deviation. Finally, we use a function signal generator to simulate the input signals of ECoG, ECG, and EOG, then use front-end circuits to read and reconstruct them to demonstrate that the proposed pixel interface can correctly read common biomedical signals for healthcare applications. © 2022 IEEE.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

A Data-Driven Approach for Online Phishing Activity Detection

A Data-Driven Approach for Online Phishing Activity Detectio...

引用

2024 International Conference on Advances in Computing, Communication, electrical, and Smart Systems, iCACCESS 2024

作者： Ahmad, Kazi Injimam Paul, Anirban Hafiz, Md. Ferdous Bin Chakraborty, Sovon Khan, Niaz Ashraf Dipto, Shakib Mahmud East Delta University Department of Computer Science and Engineering Chittagong Bangladesh University of Liberal Arts Bangladesh Department of Computer Science and Engineering Dhaka Bangladesh

ISBN: (纸本)9798350350289

The exponential rise in online activity has increased the possibility of phishing attempts, which can seriously jeopardize sensitive data and put companies and individuals at risk. This study uses cutting-edge machine learning and deep learning approaches to solve the urgent need to identify phishing websites efficiently. The proposed research utilizes two different extensive datasets with 30 and 87 features, respectively, that have been extracted from various network traffic, site content, and URLs to broadly measure the binary classification performance and accuracy of 5 different machine learning models as well as 3 deep learning-based models. Furthermore, this research employed one of the most popular feature selection techniques, Pearson correlation, to reduce the number of input variables, minimizing the amount of redundant or irrelevant features in the datasets. Training our machine learning and deep learning models with the resulting mostly redundancy-free subset of features was very efficient and with the addition of hyperparameter tuning and 10-fold cross-validation, our models produced some of the most accurate prediction results in web phishing detection. Among all the tests, the Random Forest algorithm performed better in the limited-sized dataset and scored a prediction accuracy of 97.83%. On the larger dataset, eXtreme Gradient Boosting performed slightly better and achieved a prediction accuracy of 97.02%. © 2024 IEEE.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Classification of Distress Alarms in Intensive Care Unit Using Neural Network 4

Classification of Distress Alarms in Intensive Care Unit Usi...

引用

4th International Conference on Ubiquitous Computing and Intelligent Information Systems, ICUIS 2024

作者： Latha, B. Mridhula, S. Aishvarya, R. Darshna, S.Shreeya Sri Sairam Engineering College Department of Computer Science and Engineering Chennai India

ISBN: (纸本)9798331529635

Intensive care units (ICUs) are dedicated to the treatment of patients with severe or life-threatening illnesses and injuries, necessitating constant care, close supervision, and the use of life support equipment and medications to maintain normal bodily functions. In ICUs, the monitoring of patients' physiological parameters has significantly advanced patient safety by alerting ICU staff through visual or audible alarms. However, due to understaffing during night shifts, nurses may not be able to respond promptly to these alarms, potentially endangering patient lives. Moreover, the continuous exposure of medical staff to alarms may lead to decreased concentration and errors, as well as desensitization to critical alarms, further compromising patient safety. The proposed solution utilizes a neural network to classify distress alarms in the ICU and direct them to a nurse station for timely response. © 2024 IEEE.

关键词： Nursing

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：