检索结果-内蒙古大学图书馆

International Symposium on computer, Consumer and Control (IS3C)

作者： Chia-Chen Lin Pei-Yu Wang Yan-Heng Lin Hsuan-Chao Huang Morteza Saberikamposhti Dept.of Computer Science and Information Engineering National Chin-Yi University of Technology Taichung Taiwan Dept. of Information Science & Technology Universiti Kebangsaan Malaysia Selangor Malasiya

Watermarking is a technique used to assert ownership over an image, and can be categorized into visible and invisible forms based on the detectability of the watermark. Visible watermarking is more user-friendly and intuitive than invisible methods since it allows individuals to identify image ownership with their own eyes rather than relying on machine-based watermark decoders. To enhance the visual quality of watermarked images and ensure the original images can be fully recovered after visible watermark authentication, a visible watermark removal approach using deep learning-based inpainting is proposed in this paper. Experimental results demonstrate that the watermarked images carrying the visible watermark and auxiliary information achieve peak signal-to-noise ratios (PSNRs) ranging from 41.89 dB to 43.17 dB and structural similarity indices (SSIMs) up to 0.97 to 0.98. Furthermore, our hybrid recovery operations enable the complete restoration of the original images, making them easily readable.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Pharmacy Location and Recommendation Services

Pharmacy Location and Recommendation Services

引用

IEEE International Conference on System, Computation, Automation and Networking (ICSCAN)

作者： R. Dhanalakshmi N. Vijayaraghavan R Valli Sahaya Beni Prathiba Centre for Cyber Physical Systems School of Computer Science and Engineering Vellore Institute of Technology Chennai Dept.of Mathematics KCG College of Technology Chennai India Dept.of Electronics and Communication Manakula Vinayagar Institute of Technology Puducherry India

The medical sector has continually advanced in recent years. The integration of medical services with a centralized system, on the other hand, is effective in enhancing people's lives thanks to the technology that is currently available. This system will help people to make out their medicinal requirements in their nearby location. If the exact medicine is not available alternative medicines are recommended based on user searched medicine combination it is achieved by using the rank-based algorithm to find similar medicine. This approach will computerize all pharmacy records so that customers and pharmacists can access them whenever and wherever they choose. The proposed system is to lay out a plan of action to the consumers plus pharmacist and do the representation of web services between them. This system intensifies the engagement of unorganized pharmacies into the computerized system to lift medical assistance. In such a way, the system will become the forthcoming way of e-medicinal services and advances the approach of medicinal assistance that are given to the patients by hospitals and doctors. It also helps to get drug availability in every locality

关键词：

来源：评论

学校读者我要写书评

暂无评论

Synchrosqueezed Wavelet transform Based Power Quality Disturbance Detection and Monitoring of Solar Integrated Micro-Grid

Synchrosqueezed Wavelet transform Based Power Quality Distur...

引用

Power Electronics and Energy (ICPEE), International Conference on

作者： Debasish Pattanaik Sarat Chandra Swain Indu Sekhar Samanta Ullash Kumar Rout Ritesh Dash Kunjabihari Swain School of Electrical Engineering KIIT Deemed to be University Bhubaneswar India Dept.of Computer Science and Engineering ITER SOA University Bhubaneswar India Dept. of Electrical Engineering Odisha University of Technology and Research Bhubaneswar India Dept.of Electrical and Electronics Engineering REVA University Bangalore India Dept. of Electrical and Electronics Engineering NIST Institute of Science and Technology Berhampur India

Microgrid monitoring has gained popularity in recent years, owing to their popularity and the power quality disturbances (PQD) caused by renewable energies. Many artificial intelligence-based PQD monitoring strategies have been proposed by researchers. This paper presents a novel method for detecting, classifying and monitoring the power quality disturbances in solar integrated microgrids. Power quality events are detected by analysing the frequency signal with the wavelet synchro-squeezing transform (WSST). The features of power quality disturbances are used to classify them. For PQD classification, the retrieved features are fed into a Convolutional neural network (CNN) classifier, using GoogLeNet and SqueezeNetfier. Thus the accuracy was found to be 99.90% and 93.76% respectively.

关键词： Time-frequency analysis Renewable energy sources Continuous wavelet transforms Power quality Transfer learning Microgrids Wavelet analysis

来源：评论

学校读者我要写书评

暂无评论

Deep Neural Networks in Social Media Forensics: Unveiling Suspicious Patterns and Advancing Investigations on Twitter

Deep Neural Networks in Social Media Forensics: Unveiling Su...

引用

Intelligent Cybersecurity Conference (ICSC)

作者： Yousef Sharrab Dimah Al-Fraihat Mohammad Alsmirat Dept. of Data Science and Artificial Intelligence Isra University Amman Jordan Dept.of Software Engineering Isra University Amman Jordan Dept. of Computer Science University of Sharjah Sharjah UAE

Text data forensics, a rapidly developing field that focuses on analyzing textual content to identify criminal or suspicious activities, is becoming increasingly important due to the popularity and the huge number of text posts on social media platforms. This study aims to improve the detection of suspicious text on social media using deep neural networks. Suspicious text is defined as any text that is likely to be associated with criminal activity or is unusual or out of the ordinary. This study could make a significant contribution to the field of text data forensics by helping to improve the detection of such text. We leveraged the “CIC Truth Seeker Dataset 2023” [1], which is widely recognized as a comprehensive and representative dataset for text data forensics research. The dataset contains over 180,000 tweets related to 700 real and 700 fake pieces of news, labeled by experts. In this study, we enhance text data forensics in social media by leveraging the powerful analytical capabilities of deep neural networks. More specifically, we investigate the effectiveness of Long Short-Term Memory (LSTM) in the detection of suspicious text. The results are very promising as we achieved an accuracy of 96% during preliminary evaluations. We plan to explore future work on the model's potential applications, including criminal activity identification, misinformation detection, and online harassment prevention.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An Intelligent Security Systems in Cloud Computing using Cryptography Techniques

An Intelligent Security Systems in Cloud Computing using Cry...

引用

Electronics and Sustainable Communication Systems (ICESC), 2020 International Conference on

作者： V Srilakshmi V Lakshmi Chetana Raghunadha Reddi Dornala S Parvathi Vallabaneni Ganji Ramanjaiah School of Computer Science and Engineering VIT -AP University Amaravati Andhra Pradesh India Department of Computer Science and Engineering School of Computing Amrita Vishwa Vidyapeetham India Walgreens USA Department of IT PVP Siddhartha Institute of Technology Vijayawada INDIA Dept.of CSE R V Institute of Technology GUNTUR

ISBN: (数字)9798350379945

ISBN: (纸本)9798350379952

Delivering computing resources over the internet has seen a paradigm shift towards cloud computing. However, there are serious security risks because cloud environments are distributed and shared. Intelligent Security Systems (ISS) that use cryptographic techniques are now necessary to overcome these issues, such as data confidentiality, integrity, and authenticity; this study developed an ISS for cloud computing, concentrating on cryptographic techniques. The RSA-OAEP (Optimal Asymmetric Encryption Padding) and X.509 algorithms are combined to create the ISS and further cover a variety of cryptographic methods, emphasizing their functions in protecting cloud-based systems, including encryption, digital signatures, and key management. It also looks at improving security systems' threat detection and response capabilities by integrating artificial intelligence (AI) algorithms like Grubbs' Test. In addition, several issues and potential paths for intelligent security systems in cloud computing are examined, highlighting the necessity of ongoing study and development to remain ahead of developing cyber threats.

关键词： Cloud computing ISO Standards Standardization NIST Threat assessment Libraries Encryption Security Artificial intelligence Interoperability

来源：评论

学校读者我要写书评

暂无评论

Evaluation of Block-Chain Transaction Accuracy using Neural Network Model 2

Evaluation of Block-Chain Transaction Accuracy using Neural ...

引用

2nd International Conference on Advance Computing and Innovative Technologies in engineering, ICACITE 2022

作者： Veeraiah, Vivek Suthar, Vishal Reddy, Algubelly Yashwanth Dahiya, Omdev Azam, Mohammed Kumbhkar, Makhan Adichunchanagiri University Dept. of R&d Computer Science Karnataka Mandya India Government Polytechnic College Dept. of CSE Rajasthan Jalore India Sree Dattha Group of Institutions Dept.of CSE Telangana Greater Hyderabad India Lovely Professional University School of Computer Science and Engineering Punjab Phagwara India Shri Jagdishprasad Jhabarmal Tibrewala University Dept. of ECE Rajasthan Jhunjhunu India Christian Eminent College Dept. of Computer Science MP Indore India

ISBN: (纸本)9781665437899

Block chain is known as distributed ledger technology (DLT). A distributed ledger, near real-time updates, chronological and time-stamped, cryptographically sealed, and programmable contracts are the core aspects of Block chain Technology. Brain cells, known as biological neurons, are used to implement deep learning in Neural Networks. A consequence of this is the implementation of deep learning by means of neural networks with several hidden layers. A lot of the recent work in financial transactions has focused on the intersection between block chain and artificial intelligence (AI). Artificial neural networks of this type are included. AI can help to lower the carbon impact of block chain technology. The cost and energy consumption of mining operations will be reduced significantly if AI machines replace human miners. © 2022 IEEE.

关键词： Distributed ledger

来源：评论

学校读者我要写书评

暂无评论

Endoscopic Image Processing: Evaluating the Robustness of Deep Neural Networks 5

Endoscopic Image Processing: Evaluating the Robustness of De...

引用

5th International Conference on Smart Electronics and Communication, ICOSEC 2024

作者： Gireesh Babu, C.N. Babu, Kaparapu Satish Suneel, Sajja Rao, K.Srinivasa Muralitharan, Divya Aarthi, R. Bms Institute of Technology and Management Dept.of CSE/ISE Karnataka Bengaluru India Geetanjali College of Engineering and Technology Department of Electronics and Communication Engineering Telangana Hyderabad India Hyderabad Telangana Dundigal500043 India K.S.R.M. College of Engineering Department of Ai&ml Andhra Pradesh Kadapa516003 India Vel Tech Rangarajan Dr. Sagunthala R&d Institute of Science and Technology Department of Computer Science and Engineering Chennai India R.M.D Engineering College Department of Ece R. S. M Nagar Gummidipoondi601206 India

ISBN: (纸本)9798331504403

The Hybrid CNN-Transformer Model (HCNNT) is a novel model which exploits Convolutional Neural Networks (CNN) for spatial feature extraction and Transformers for capturing contextual and long range dependencies in order to carry complex image classification. In order to evaluate the algorithm proposed, a new model has been introduced and trained on a data set of gastrointestinal (GI) image classification, which is derived from a balanced data set with 226 images available on Kaggle. Although the cascaded CNN part is to learn elaborate visual characteristics, the improved understanding of complex patterns and relationships is achieved by the Transformer component to process these features. When both are integrated, we gain a powerful system that has high accuracy in distinguishing GI bleeding condition from normal condition. Extensive training and optimization of the hybrid model using binary cross-entropy loss and Adam optimizer has achieved state-of-the-art performance. Through the experiments evaluated on the HCNNT model, it is evident that an accuracy of 97.34% proves to be significantly beneficial, its practicality in terms of reliability for medical image classification that essentially improves the accuracy of diagnosis in gastrointestinal healthcare. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

A comparative study for lung, colon and breast cancer diagnosis using different convolutional neural networks

A comparative study for lung, colon and breast cancer diagno...

引用

International Conference on Advances in Biomedical engineering (ICABME)

作者： Hussein Akar Jacqueline Abou Diab Fatima Sbeity Mohamad Abou Ali Abdallah Kassem Lara Hamawy Dept. of Biomedical Engineering Lebanese International University Lebanon Dept. of Physics & Electronics Lebanese University Lebanon Dept.of Computer Science & Artificial Intelligence University of the Basque Country Spain Dept. of Electrical &Computer Engineering Notre Dame University Lebanon

In modern times, the prevalence of diseases, particularly cancer, is rising rapidly. Diagnostic errors pose a critical safety concern in healthcare due to the complexity of medical decision-making, disease variability, and human cognitive limitations. This paper aims to compare different convolutional neural networks (CNNs) to find the most accurate model that can classify lung, colon, and breast cancer using histopathological images. A convolutional neural network is a subset of machine learning. It is one of the various types of artificial neural networks which are used for different applications and data types. A CNN is a kind of network architecture for deep learning algorithms and is specifically used for image recognition and tasks that involve the processing of pixel data. We created a baseline model that consists of a basic CNN architecture. It serves as a starting point for comparison with more complicated models. The baseline model's performance is then compared to the performance of various pretrained models (ResNet-50, ResNet-101, VGG-16, VGG-19, Inception V3, and DenseNet-121). The dataset used consists of 25,000 histopathological images of both the lung and colon and 277,000 histopathological of breast images. Results show that the ResNet-50 model is the most efficient among all the other models, scoring a validation accuracy of 98.3%. Additionally, ResNet-101, VGG-16, VGG-19, and DenseNet-121 also demonstrated strong performance, scoring 95.8%, 96.6%, 95.1%, and 92.4%, respectively. Meanwhile, Inception-V3displayed a fair result, scoring a validation accuracy of 73.2%.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Under the surface:Pressure-induced planetary-scale waves,volcanic lightning,and gaseous clouds caused by the submarine eruption of Hunga Tonga-Hunga Ha'apai volcano

引用

Earthquake Research Advances 2022年第3期2卷 1-13页

作者： David A.Yuen Melissa A.Scruggs Frank J.Spera Yingcai Zheng Hao Hu Stephen R.McNutt Glenn Thompson Kyle Mandli Barry R.Keller Songqiao Shawn Wei Zhigang Peng Zili Zhou Francesco Mulargia Yuichiro Tanioka Columbia University Dept.of Applied Physics and Applied MathematicsNew YorkNY10027USA Ocean University of China School of Computer Science and Marine GeosciencesQingdao266100China University of California Santa BarbaraDept.of Earth Science1006 Webb HallUniversity of CaliforniaSanta BarbaraCA93106USA University of Houston Dept.of Earth and Atmospheric SciencesScience&Research Bldg.13507 Cullen Boulevard#312HoustonTX77004USA University of South Florida School of GeosciencesTampaFLUSA Mission Beach CAUSA Michigan State University Dept.of Earth and Environmental Sciences288 Farm Ln BldgRoom 207East LansingMI48824USA Georgia Institute of Technology School of Atmospheric and Earth SciencesNorth AvenueAtlantaGA30332USA University of Southern California Sonny Astani Dept.of Civil&Environmental EngineeringKaprielian HallLos AngelesCA90089-2531USA University of Bologna Dept.of Geological SciencesVia Zamboni3340126BolognaItaly Hokkaido University Division of Earth System ScienceN10W5SapporoHokkaido060-0810Japan

We present a narrative of the eruptive events culminating in the cataclysmic January 15, 2022 eruption of Hunga Tonga-Hunga Ha’apai Volcano by synthesizing diverse preliminary seismic, volcanological, sound wave, and lightning data available within the first few weeks after the eruption occurred. The first hour of eruptive activity produced fast-propagating tsunami waves, long-period seismic waves, loud audible sound waves, infrasonic waves, exceptionally intense volcanic lightning and an unsteady volcanic plume that transiently reached-at 58km-the Earth’s mesosphere. Energetic seismic signals were recorded worldwide and the globally stacked seismogram showed episodic seismic events within the most intense periods of phreatoplinian activity, and they correlated well with the infrasound pressure waveform recorded in Fiji. Gravity wave signals were strong enough to be observed over the entire planet in just the first few hours, with some circling the Earth multiple times subsequently. These large-amplitude, long-wavelength atmospheric disturbances come from the Earth’s atmosphere being forced by the magmatic mixture of tephra, melt and gasses emitted by the unsteady but quasicontinuous eruption from 0402±1–1800 UTC on January 15, 2022. Atmospheric forcing lasted much longer than rupturing from large earthquakes recorded on modern instruments, producing a type of shock wave that originated from the interaction between compressed air and ambient(wavy) sea surface. This scenario differs from conventional ideas of earthquake slip, landslides, or caldera collapse-generated tsunami waves because of the enormous(~1000x) volumetric change due to the supercritical nature of volatiles associated with the hot,volatile-rich phreatoplinian plume. The time series of plume altitude can be translated to volumetric discharge and mass flow rate. For an eruption duration of ~12 h, the eruptive volume and mass are estimated at 1.9 km^(3) and~2 900 Tg, respectively, corresponding to a VEI

关键词： Hunga Tonga-Hunga Ha'apai Atmospheric pressure wave Tsunami wave Volcanic lightning Phreatoplinian eruption

来源：评论

学校读者我要写书评

暂无评论

Smart Conversations: Enhancing User Engagement through NLP in IoT Environments

Smart Conversations: Enhancing User Engagement through NLP i...

引用

International Conference on Reliability, Infocom Technologies and Optimization (ICRITO) (Trends and Future Directions)

作者： G. Muthugurunathan S. Padmapriya L. Leelavathy Veera Talukdar Ankur Gupta Manisha Mittal Dept. of CSE Madanapalle Institute of Technology & Science Andhra Pradesh India Dept. of Computer Science SRM Trichy Arts and Science College Irungalur TN India Dept.of CS D Y Patil International University Akurdi Pune Maharashtra India Dept.of CSE Vaish College of Engineering Rohtak Haryana India Dept. of ECE Guru Tegh Bahadur Institute of Technology GGSIPU New Delhi India

ISBN: (数字)9798350350357

ISBN: (纸本)9798350350364

The integration of NLP into IoT settings has emerged as a revolutionary framework, providing consumers with a more intuitive and participatory experience. This study examines the capacity of NLP to improve user involvement in IoT ecosystems by facilitating intelligent interactions between people and linked objects. The exponential growth of IoT devices has resulted in a surge of data, necessitating the development of efficient and user-friendly interfaces to facilitate smooth interactions. NLP is crucial in connecting people and IoT devices by enabling the comprehension and production of language that resembles human communication. By adding NLP, IoT environments may give users with a conversational interface, allowing them to manage and monitor equipment with natural language instructions. This study focuses on doing a comprehensive examination of current NLP approaches and their suitability for use in IoT environments. This work examines the problems and potential of integrating NLP in various IoT situations. It specifically focuses on tackling concerns related to language variety, contextual comprehension, and the need for real-time processing. Moreover, the research examines the influence of intelligent dialogues on user involvement, highlighting the possibility of heightened user contentment, effectiveness, and availability. Case studies and practical examples demonstrate effective use of NLP in IoT applications.

关键词： Natural languages Production Oral communication Turning User experience Real-time systems Internet of Things

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：