检索结果-内蒙古大学图书馆

4th International Conference on Emerging Research in Electronics, computer Science and Technology, ICERECT 2022

作者： Dubey, Abhishek Kumar, Vijay Singhal, Priyank Savyasachi Ul Islam, Atowar Kuppuchamy, R. Chandigarh Engineering College Department of CSE Jhanjeri India JAIN University Department of CSE Bangalore India Mahaveer University Department of Computing Sciences & IT Moradabad India Lalit Narayan Mishra College of Business Management Department of Information Technology Bihar Muzaffarpur India University of Science and Technology Dept. of Computer Science and Electronics Meghalaya Techno City India PSNA College of Engineering and Technology Department of Computer Applications Dindigul India

ISBN: (纸本)9781665456357

Scientists in academia and business have thoroughly studied Encryption Scheme (SE). Whereas many scientific SE methods provide verifiable confidentiality, in order to attain high performance, they typically reveal certain 'trans (such as search and access patterns). Yet, a number of infer methods have taken advantage of this leaking, for instance, a query recovering attack that uses foreknowledge to convert transparent question passageways to their matching keywords. But at the other hand, several more pro - posed SE schemes require substantial modification applications, that also tends to make them less convenient, weak in user experience, and complicated to deploy. In this research, we offer IDCrypt, a safe and useful Is the Enclosure (SSE) scheme with demonstrable security power for azure. IDCrypt uses cryptographic techniques to increase SE's security level and search efficiency. We also highlight the key difficulties in safely sharing decrypted data across different individuals and search across several indexes. We suggest a coin search strategy to maintain the search features across several indexes or a key sharing system that combines Personality Crypto (IBE) with Community Encrypted data to solve the aforementioned problems (PKE). Our empirical findings demonstrate that the number of key agreement's expense is rather modest. © 2022 IEEE.

关键词： Cryptography

来源：评论

学校读者我要写书评

暂无评论

Enhanced Filtering Techniques for an Advanced Fingerprint Recognition System

Enhanced Filtering Techniques for an Advanced Fingerprint Re...

引用

Communication & computing (WCONF), World Conference on

作者： Gaurav Kumar Ankur Sharma Ankit Kumar Kamred Udham Singh Teekam Singh Tanupriya Choudhury Department of Computer Engineering & Applications GLA University Mathura UP India Department of Computer Applications ITS Mohan Nagar Ghaziabad India School of Computing Graphic Era Hill University Dehradun India Department of Computer Science and Engineering Graphic Era Deemed to be University Dehradun India CSE Dept. Graphic Era Hill University Dehradun Uttarakhand India Director Research (Honorary) The AI University Cutbank Montana US

Human fingerprint artifacts, the surrounding environment, and the fingerprint-collecting equipment all contribute to less-than-ideal fingerprint images. Most digital photographs have extraneous details because of these image-altering effects. Therefore, a number of substantial changes are required to improve the efficacy of FRS. In the practice of enhancing an image by applying methods like filtering to boost its quality. Image filtering is a method that can enhance an image by eliminating unwanted details and minimizing noise. The process of picture filtering also includes other steps, such as smoothing and sharpening the original image. In this study, we developed an approach in which several filters, such as the Unsharp, Gaussian, and Averaging filters, are applied to the original picture. Experimental findings demonstrate that the ‘Unsharp filter’ improves image quality when using this kind of compression between filters.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Citizen Science for the Sea with Information Technologies: An Open Platform for Gathering Marine Data and Marine Litter Detection from Leisure Boat Instruments

Citizen Science for the Sea with Information Technologies: A...

引用

IEEE International Conference on e-Science and Grid computing

作者： Ciro Giuseppe De Vita Gennaro Mellone Dante D. Sanchez-Gallegos Giuseppe Coviello Diego Romano Marco Lapegna Angelo Ciaramella Dept. of Science and Technology University of Naples “Parthenope” Naples Italy Dept. of Computer Science University of Madrid Carlos III Madrid Spain NEC Laboratories of America Inc. Princeton NJ USA Inst. for High Performance Computing and Networking (ICAR) National Research Council (CNR) Naples Italy Dept. of Mathematics and Applications University of Naples “Federico II” Naples Italy

Data crowdsourcing is an increasingly pervasive and lifestyle-changing technology due to the flywheel effect that results from the interaction between the Internet of Things and Cloud computing. This paper presents the Citizen Science for the Sea with Information Technologies (C4Sea-IT) framework. It is an open platform for gathering marine data from leisure boat instruments. C4Sea-IT aims to provide a coastal marine data gathering, moving, processing, exchange, and sharing platform using the existing navigation instruments and sensors for today's leisure and professional vessels. In this work, a use case for the detection and tracking of marine litter is shown. The final goal is weather/ocean forecasts argumentation with Artificial Intelligence prediction models trained with crowdsourced data.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Facial Emotion Analysis using Deep Learning for Seamless Human-computer Interaction

Facial Emotion Analysis using Deep Learning for Seamless Hum...

引用

Network, Multimedia and Information Technology (NMITCON) International Conference on

作者： S Sangeetha Poonam Saini R Banupriya S Srimathi S Kiruthiga R Aarthi Department of computer Applications and Technology SRM Arts and Science College Kattankulathur Changelpattu Dept. of Computer Science & Engineering Sir Padampat Singhania University Vil. Bhatewar Teh. Vallabhnagar Udaipur Rajasthan Dept. of Electrical and Electronics Engineering PGP College Of Engineering and Technology Department of Bio Technology Saveetha School of Engineering SIMATS Chennai Tamilnadu India Department of Computer Science & Engineering School of Computing Vel Tech Rangarajan Dr Sagunthala R & D Institute of Science & Technology Chennai Department of ECE R.M.D Engineering College

ISBN: (数字)9798350372892

ISBN: (纸本)9798350372908

HCII, or human-computer intelligent interaction, is a new academic subject that tries to make computer use more intuitive. Some say machines need human-level social abilities before interacting with people. These skills include reading emotions. Due to its exponential expansion, facial emotion recognition is becoming essential to face recognition. According on photographs, machine learning can recognise expressions. This paper discusses expression recognition model training datasets. Deep learning for Facial Emotion Recognition (FER) is used in this research to teach robots to recognise and adapt to human emotions. An extensive review of deep learning models, including CNNs and CNNR, emphasises their ability to extract spatial and temporal data needed for emotion classification. FER pipeline components like data collection, preprocessing, and model architecture are examined in the paper. Transfer learning, pre-trained models, and data augmentation are studied to address low-labeled dataset concerns. Detailed model training, validation, and evaluation metrics emphasise performance assessment. This study uses the enlarged CohnKanade (CK+) dataset from a face emotion recognition experiment. The system averaged 92.81% accuracy. Eight emotions were successfully detected by the algorithm. The proposed method for emotion recognition has proven useful.

关键词： Deep learning Training Measurement Emotion recognition Adaptation models Accuracy Face recognition Transfer learning Data models Spatial databases

来源：评论

学校读者我要写书评

暂无评论

A Hybrid Approach Towards Data optimization for Cloud Based IoT Environment

A Hybrid Approach Towards Data optimization for Cloud Based ...

引用

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

作者： Souvik Pal N. Z. Jhanjhi D. Akila Monir Abdullah Memona Humayun Sandeep Kumar Rahul Kumar Dept. of Management IS Saveetha College of Liberal Arts & Sciences Saveetha Institute of Medical & Tech. Sciences Chennai India Dept. of CS and Engineering Sister Nivedita University Kolkata India School of Computer Science SCS Taylor's University Subang Jaya Malaysia Dept. of Computer Applications Saveetha College of Liberal Arts & Sciences SIMATS Deemed University hennai India Department of CS and AI College of Computing & IT University of Bisha Bisha Saudi Arabia Department of Computing School of Arts Humanities & Social Sciences University of Roehampton London United Kingdom Division of Research and Development Lovely Professional University Phagwara-144411 India KKR and KSR Institute of Technology and Sciences Guntur Andhra Pradesh India

ISBN: (数字)9798350353266

ISBN: (纸本)9798350353273

An innovative method for data optimization in the Internet of Things (IoT) assister sensing devices is presented in this research. The many elements of the cloud platform with IoT assistance are addressed. A fresh design for IoT-aided sensor networks is introduced to monitor the environment. A Data Optimisation in Cloud Internet of Things (DO-CIoT) is proposed in this paper to optimize the data stored in the cloud and presents methods to access the data in end devices. The suggested technique uses a membership function to improve data allocation while considering all node data. The suggested model is assessed regarding performance ratios, reliability percentage, coverage ratios, and sensing error and contrasted with two-stage efficiency enhancement. A mean performance ratio of 89%, reliability of 91%, coverage of 89

关键词： Performance evaluation Cloud computing computer network reliability Market research Sensors Internet of Things Reliability Resource management Optimization Monitoring

来源：评论

学校读者我要写书评

暂无评论

Detection and Classification of Diseases in Rice Crops from Its Leaves by Using Machine Learning Algorithm

Detection and Classification of Diseases in Rice Crops from ...

引用

Information Technology (OCIT), OITS International Conference on

作者： Patrick Ansah Arup Kumar Mukherjee Vinh Truong Hoang Ankita Mandal Satya Ranjan Dash Obed Adjei Peprah Dept. of Computer Science University of West Florida Florida USA ICAR-National Rice Research Institute Cuttack India Faculty of Information Technology Ho Chi Minh City Open University Vietnam School of Biotechnology Kalinga Institute of Industrial Technology Bhubaneswar India School of Computer Applications KIIT University Bhubaneswar India Department of Computing and Electronics Eng. Atlantic Tech. University Sligo Ireland

ISBN: (数字)9798331510404

ISBN: (纸本)9798331510411

Diseases and pests are affecting rice crops globally which is becoming a major threat to our food security. Loss of rice crops needs to be prevented to avoid any disruptions in the food supply. Due to the lack of infrastructure in many parts of the world, rapid identification and classification of diseases in rice crops were not possible. But with the advancement of technologies in terms of computer applications such as Machine Learning (ML), Artificial Intelligence (AI), and Smart computing techniques, diagnosis of diseases in rice crops can be made possible. Technology is getting smarter nowadays, so implementation of these technologies would help the agricultural sector to accept the new changes and move on from its traditional ways. There are instances where manual examination of rice crops are not possible, so these technologies help a lot. In this paper, we have presented a type of supervised machine learning algorithm called Convolution Neural Networking (CNN), which was used for the classification and identification of the diseases affecting the rice crops. Further with the help of Keras, Python and TensorFlow the huge sample dataset collected was helpful in prediction of the diseases.

关键词： Machine learning algorithms Crops Food security Production Machine learning Manuals Inspection Medical diagnosis Diseases Python

来源：评论

学校读者我要写书评

暂无评论

DUNE Software and High Performance computing

arXiv

引用

arXiv 2022年

作者： Fleming, Bonnie Knoepfel, Kyle Lin, Meifeng Qian, Xin Ren, Yihui Viren, Brett Wei, Hanyu Yoo, Shinjae Yu, Haiwang Dept. of Physics Brookhaven National Laboratory United States Computer Science Brookhaven National Laboratory United States Dept. of Physics Yale University United States Dept. of Physics and Astronomy Louisiana State University United States Scientific Computing Division Fermi National Accelerator Laboratory United States

DUNE, like other HEP experiments, faces a challenge related to matching execution patterns of our production simulation and data processing software to the limitations imposed by modern high-performance computing facilities. In order to efficiently exploit these new architectures, particularly those with high CPU core counts and GPU accelerators, our existing software execution models require adaptation. In addition, the large size of individual units of raw data from the far detector modules pose an additional challenge somewhat unique to DUNE. Here we describe some of these problems and how we begin to solve them today with existing software frameworks and toolkits. We also describe ways we may leverage these existing software architectures to attack remaining problems going forward. This whitepaper is a contribution to the Computational Frontier of Snowmass21. © 2022, CC BY.

关键词： Data handling

来源：评论

学校读者我要写书评

暂无评论

Detection And Classification Of Diseases In Rice Crops From Its Leaves By Using Machine Learning Algorithm 22

Detection And Classification Of Diseases In Rice Crops From ...

引用

22nd OITS International Conference on Information Technology, OCIT 2024

作者： Ansah, Patrick Mukherjee, Arup Kumar Hoang, Vinh Truong Mandal, Ankita Dash, Satya Ranjan Peprah, Obed Adjei Dept. of Computer Science University of West Florida FL United States ICAR-National Rice Research Institute Cuttack India Faculty of Information Technology Ho Chi Minh City Open University Viet Nam School of Biotechnology Kalinga Institute of Industrial Technology Bhubaneswar India School of Computer Applications KIIT University Bhubaneswar India Department of Computing and Electronics Eng. Atlantic Tech. University Sligo Ireland

ISBN: (纸本)9798331510404

关键词： Learning algorithms

来源：评论

学校读者我要写书评

暂无评论

Customer Lifetime Value Prediction: Using Machine Learning to Forecast CLV and Enhance Customer Relationship Management

Customer Lifetime Value Prediction: Using Machine Learning t...

引用

International Symposium on Multidisciplinary Studies and Innovative Technologies (ISMSIT)

作者： Ankit Kumar Kamred Udham Singh Gaurav Kumar Tanupriya Choudhury Ketan Kotecha Department of Computer Engineering & Applications GLA University Mathura UP India School of Computing Graphic Era Hill University Dehradun India CSE Dept. Symbiosis Institute of Technology Symbiosis International (Deemed University) Pune India Symbiosis Centre for Applied Artificial Intelligence Symbiosis Institute of Technology Symbiosis International (Deemed University) Pune India

In today's cutthroat corporate realm, consistent innovation and market adaptability don't cut it; mastering client relationships is key. A pivotal metric here is the Customer Lifetime Value (CLV), shedding light on long-term profit potentials per customer, an understanding of which is critical for business growth. A study delves into enhancing Customer Relationship Management (CRM) using machine learning to refine CLV predictions. Conducted collaboratively, it explores CLV's role in marketing, client segmentation, and resource optimization before delving into its measurement. Using advanced machine learning tools like regression, clustering, and neural networks on a rich dataset of customer transactions and behaviors, it's found that machine learning significantly outperforms traditional CLV estimation methods. This leads to better CLV accuracy and paves the way for enhanced resource allocation and targeted marketing, further emphasizing CLV's importance in crafting personalized customer journeys and refining CRM strategies amidst a constantly evolving market landscape.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A scalable generative model for dynamical system reconstruction from neuroimaging data 24

A scalable generative model for dynamical system reconstruct...

引用

Proceedings of the 38th International Conference on Neural Information Processing Systems

作者： Eric Volkmann Alena Brändle Daniel Durstewitz Georgia Koppe Department of Theoretical Neuroscience Central Institute of Mental Health (CIMH) Medical Faculty Mannheim Heidelberg University Mannheim Germany and Institute for Machine Learning Johannes Kepler University Linz Austria Department of Theoretical Neuroscience Central Institute of Mental Health (CIMH) Medical Faculty Mannheim Heidelberg University Mannheim Germany and Interdisciplinary Center for Scientific Computing Heidelberg University Heidelberg Germany and Faculty of Physics and Astronomy Heidelberg University Heidelberg Germany Interdisciplinary Center for Scientific Computing Heidelberg University Heidelberg Germany and Hector Institute for AI in Psychiatry & Dept. for Psychiatry and Psychotherapy CIMH and Faculty of Mathematics and Computer Science Heidelberg University Heidelberg Germany

ISBN: (纸本)9798331314385

Data-driven inference of the generative dynamics underlying a set of observed time series is of growing interest in machine learning and the natural sciences. In neuroscience, such methods promise to alleviate the need to handcraft models based on biophysical principles and allow to automatize the inference of inter-individual differences in brain dynamics. Recent breakthroughs in training techniques for state space models (SSMs) specifically geared toward dynamical systems (DS) reconstruction (DSR) enable to recover the underlying system including its geometrical (attractor) and long-term statistical invariants from even short time series. These techniques are based on control-theoretic ideas, like modern variants of teacher forcing (TF), to ensure stable loss gradient propagation while training. However, as it currently stands, these techniques are not directly applicable to data modalities where current observations depend on an entire history of previous states due to a signal's filtering properties, as common in neuroscience (and physiology more generally). Prominent examples are the blood oxygenation level dependent (BOLD) signal in functional magnetic resonance imaging (fMRI) or Ca2+ imaging data. Such types of signals render the SSM's decoder model non-invertible, a requirement for previous TF-based methods. Here, exploiting the recent success of control techniques for training SSMs, we propose a novel algorithm that solves this problem and scales exceptionally well with model dimensionality and filter length. We demonstrate its efficiency in reconstructing dynamical systems, including their state space geometry and long-term temporal properties, from just short BOLD time series.

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：