检索结果-内蒙古大学图书馆

Sustainable Computing and Smart Systems (ICSCSS), International Conference on

作者： Harini. S J. Praveenchandar Department of Computer Science and Engineering Karunya Institute of Technology and Sciences Coimbatore Division of Artificial Intelligence and Machine Learning Karunya Institute of Technology and Sciences Coimbatore

ISBN: (数字)9798350379990

ISBN: (纸本)9798350391558

There are various online web sites available nowadays. People are using online web sites for shopping etc. So take a particular website to scrape the data present in it. Choose *** to fetch the price of the product and display it according to the user's feed. Reach that website and the price of the product may changes according to the seasons, festivals, or some special events. So it fetches the price of the current date and provide it to the user's feed. Additionally, the date and time for the particular product is included. Here BeautifulSoup and pyspark are used. Here they use scraping tactics, specifically, in the realm of online advertising. In order to do this, this study suggests a collaborative filtering-based Web advertising system that makes use of Web scraping to identify the most pertinent ads for a generic Web page. Scrapers are especially interested in converting unstructured material and storing it in organized databases. Web scraping is a software method that gathers data from websites by using appropriate web browsers or low-level Hyper Text Transfer Protocol (HTTP) to mimic human exploration of the World Wide Web 1. It is closely associated with web indexing, which extracts information from the web using bots that have been designed by humans. The primary goal of Web Scraping is to convert unstructured data-typically in HTML format-into structured data that can be stored and handled in a centralized database 1. This technique is frequently utilized for a number of different tasks, including pricing comparison, mashups or mix-ups of webpages, weather prediction information, webpage integration, and webpage interface change detection. Some of the challenges are IP Blocking and Rate limiting, Dynamic content Loading, etc.

关键词： Databases Heuristic algorithms Web pages Weather forecasting Web sites Feeds Data mining

来源：评论

学校读者我要写书评

暂无评论

Deep learning-Based Dynamic Scheduling for Semiconductor Manufacturing with High Uncertainty of Automated Material Handling System Capability 2

Deep Learning-Based Dynamic Scheduling for Semiconductor Man...

引用

2nd International Conference on Data science and Information System, ICDSIS 2024

作者： Dineshkumar, R. Al-Attabi, Kassem Kumar, Komuravelly Sudheer Madhura, G.K. Sharma, Jaya Saveetha Institute Of Medical And Technical Sciences Saveetha University Saveetha School Of Engineering Department Of Ece Chennai India The Islamic University College Of Technical Engineering Department Of Computers Techniques Engineering Najaf Iraq Sr University School Of Computer Science & Artificial Intelligence Telangana Warangal India Nitte Meenakshi Institute Of Technology Department Of Artificial Intelligence And Machine Learning Bengaluru India Gitam University Department Of Cse Bengaluru India

ISBN: (纸本)9798350381665

To improve the dynamic responsiveness and production efficiency of manufacturing workshops to personalized orders, a multi-agent manufacturing system. However, the previous methods cannot work well in a changeable workshop environment when encountering a large number of stochastic disturbances of orders and resources. Develop a robust scheduling approach for dynamic workshop environments, effectively managing stochastic disturbances in orders and resources to optimize production efficiency and minimize disruptions. Dynamic scheduling approach for semiconductor manufacturing using Proximal Policy Optimization (PPO) and Autoencoder (AE) for feature extraction, defining state space to capture task and production attributes. Action space design employs dispatching rules for operation selection, while the reward function adapts production to demand, trained in action and state phases. Autoencoders compress high-dimensional input data into a lower-dimensional latent space while preserving important features. The obtained results demonstrate that the proposed method achieves better performance Delivery Data Rate (DDR) of 41.20 %, Mean Cycle Time (MCT) of 51.66%, Mean of 12.85%, and Execution time of 5.07s. These results ensure superior dynamic scheduling performance compared to other existing methods, such as Dynamic Scheduling Using Flexible Job Shop Scheduling problem (FJSP), and Multiple-DynamicScheduling-Rule (MDSR). © 2024 IEEE.

关键词： Production efficiency

来源：评论

学校读者我要写书评

暂无评论

Detection of pulmonary embolism with improved Xception architecture

Detection of pulmonary embolism with improved Xception archi...

引用

International Conference on AI and the Digital Economy (CADE 2024)

作者： Getzi Jeba Leelipushpam Paulraj P. Joyce Beryl Princess Immanuel Johnraja Jebadurai S. Celshia Division of Computer Science and Engineering Karunya Institute of Technology and Sciences India Division of Artificial Intelligence and Machine Learning Karunya Institute of Technology and Sciences India

ISBN: (数字)9781837241842

The blocking of arteries in the lungs through blood clots is known as pulmonary embolism. This blood vessel block usually originates in the legs and travels to the lungs causing fatal damage. An imaging test called Computed Tomography (CT) pulmonary angiography scans the lungs for blood clots. The preferred method for identifying pulmonary embolism is CT pulmonary angiography. Manual examination by radiologists increases the workload, consumes more time and also requires experience for correct examination. The objective of this paper is to propose an improved Xception architecture based on Convolutional Neural Networks. The existing architecture is improvised by replacing the Relu activation function with the Swish activation function. This improves the feature extraction of the algorithm thereby improving efficiency in terms of loss and accuracy. The algorithm has been trained and tested using the standard RSNA-STR Pulmonary Embolism CT Dataset. It is evident from the experimental results that our model achieves an improvement of 3.4% and 1.4% in terms of accuracy and loss respectively.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Protecting Medical Image Transmission: Color Secret Sharing Protocol for Enhanced Security

Protecting Medical Image Transmission: Color Secret Sharing ...

引用

2024 International Conference on artificial intelligence and Quantum Computation-Based Sensor Applications, ICAIQSA 2024

作者： Maram, Balajee Sai, Manikonda Srinivasa Sesha Vanniappan, Malathy Srinivas, T. Aditya Sai Nagaraju, Pamarthi Prasan, U.D. School of Computer Science and Artificial Intelligence SR University Telangana Warangal506371 India KKR & KSR Institute of Technology and Sciences Department of Information Technology Guntur India SR University Department of Electronics and Communication Engineering Telengana Warangal India Jayaprakash Naryan College of Engineering Artificial Intelligence and Machine Learning Mahabubnagar India Department of CSE Bhimavaram India Aditya Institute of Technology and Management Andhra Pradesh Tekkali India

ISBN: (纸本)9798331517953

The safety in the transmission of medical images cannot be compromised in the digital age, as the information contained is very sensitive. This paper presents a new approach to providing security for medical image transmission using the Color Secret Sharing protocol. This is ensured by the proposed approach of dividing the medical image into many shares, each of which is encoded with independent color information, to ensure that the restoration of the original image can be done only if all the shares are combined. Thus, the risk related to unauthorized access and data breaching is much reduced during the transmission process. Security analysis and experimental validation are provided that demonstrate that the compared methods tend to efficiently resist attacks. This study embeds CSS into medical imaging systems to solve the secure and trustworthy solution on the confidentiality, integrity, and availability of patient data in healthcare communications. © 2024 IEEE.

关键词： Color Secret Sharing Cryptography Healthcare Data Protection Image Encryption Medical Image Security Secure Transmission

来源：评论

学校读者我要写书评

暂无评论

An Effective Algorithm to Enhance the Performance of Online Quiz System

An Effective Algorithm to Enhance the Performance of Online ...

引用

Sustainable Computing and Smart Systems (ICSCSS), International Conference on

作者： Arumulla Srinayana J. Praveenchandar Department of Computer Science and Engineering Karunya Institute of Technology and Sciences Coimbatore Division of Artificial Intelligence and Machine Learning Karunya Institute of Technology and Sciences Coimbatore

ISBN: (数字)9798350379990

ISBN: (纸本)9798350391558

This research study intends to develop an online quiz system that prioritizes user involvement, enjoyment, and performance. To achieve this, the proposed platform features a diverse array of quiz themes and formats, catering to a wide audience with varied interests and preferences. Unlike traditional platforms that rely on ranking systems, our application fosters a relaxed environment where users can engage with quizzes at their own pace, free from competitive pressure. Methodologically, we conducted user testing, performance monitoring, and comparative analysis with rival algorithms to assess the platform's effectiveness. The research findings indicate high levels of user satisfaction, engagement, and overall performance, along with areas for improvement identified through these evaluations. Notably, we plan to enhance the platform further based on user feedback and experimental learnings. This includes optimizing the quiz creation algorithm, implementing UI enhancements, and exploring gamification and social integration features. Our developed online quiz system thus presents a promising tool for education, collaboration, and entertainment, aiming to cultivate a welcoming and inclusive community where learning is both enjoyable and socially enriching.

关键词： Education Collaboration Entertainment industry User interfaces Green computing Monitoring Testing

来源：评论

学校读者我要写书评

暂无评论

Towards Scalable and Deep Graph Neural Networks via Noise Masking 39

Towards Scalable and Deep Graph Neural Networks via Noise Ma...

引用

39th Annual AAAI Conference on artificial intelligence, AAAI 2025

作者： Liang, Yuxuan Zhang, Wentao Sheng, Zeang Yang, Ling Xu, Quanqing Jiang, Jiawei Tong, Yunhai Cui, Bin School of Intelligence Science and Technology Peking University China Center for Machine Learning Research Peking University China Peking University China OceanBase Ant Group China School of Computer Science Wuhan University China Institute of Computational Social Science Peking University Qingdao China

ISBN: (纸本)157735897X

In recent years, Graph Neural Networks (GNNs) have achieved remarkable success in many graph mining tasks. However, scaling them to large graphs is challenging due to the high computational and storage costs of repeated feature propagation and non-linear transformation during training. One commonly employed approach to address this challenge is model-simplification, which only executes the Propagation (P) once in the pre-processing, and Combine (C) these receptive fields in different ways and then feed them into a simple model for better performance. Despite their high predictive performance and scalability, these methods still face two limitations. First, existing approaches mainly focus on exploring different C methods from the model perspective, neglecting the crucial problem of performance degradation with increasing P depth from the data-centric perspective, known as the over-smoothing problem. Second, pre-processing overhead takes up most of the end-to-end processing time, especially for large-scale graphs. To address these limitations, we present random walk with noise masking (RMask), a plug-and-play module compatible with the existing model-simplification works. This module enables the exploration of deeper GNNs while preserving their scalability. Unlike the previous model-simplification works, we focus on continuous P and found that the noise existing inside each P is the cause of the over-smoothing issue, and use the efficient masking mechanism to eliminate them. Experimental results on six real-world datasets demonstrate that model-simplification works equipped with RMask yield superior performance compared to their original version and can make a good trade-off between accuracy and efficiency. Copyright © 2025, Association for the Advancement of artificial intelligence (***). All rights reserved.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

A Genetic Algorithm Approach to Adaptive learning: Enhancing Learner Satisfaction and Performance

引用

IEEE Access 2025年 13卷 102815-102829页

作者： Anju Kalwar Deepika Shekhawat Sandeep Joshi Amit Kumar Bairwa School of Computer Science and Application JECRC University Jaipur India Department of Computer Science and Engineering Amity University Mumbai Mumbai Maharashtra India Department of Computer Science and Engineering Manipal University Jaipur Jaipur India Department of Artificial Intelligence and Machine Learning Manipal University Jaipur Jaipur India

As educational technologies mature at a growing rate, effective models of instructional delivery systems that can deliver learning experiences based on the individual learner’s learning style have also been created. One of the core elements of such systems is the ability to recommend the right content that improves the learner’s experience. The adaptative learning environment and content recommendation with the help of genetic algorithms are investigated in this paper. GA, based on the principles of Natural Selection, provides stability-based search and solving capacity needed to tackle the inherent messiness and diversity of PBL. In our approach, each learner’s context information, as well as performance metrics, preferences and learning goals, are dynamic and fed into the GA. The algorithm genetically generates a random vote of potential content sequences as the initial population that improves through creation by selection, crossover, or mutation. The fitness function assesses an individual sequence in terms of its conformity to the learner’s profile and, thus, helps to increase an LMS usage rate, select appropriate content, and achieve targeted educational objectives. The proposed system is an application of GA that constantly updates feedback from the learner’s generated performance data and adjusts the recommended content in real time. This dynamic creates a positive learning environment capable of enhancing learner interaction and improving learning achievements. When the proposed GA-based solution is applied in a specific case with an instructional design within an online learning context, enhancement in learner satisfaction and performance are substantial, sufficiently proving the approach’s applicability. Thus, this study expands the existing literature on adaptive learning technologies by including the usage of GA in education. Future work will extend this by investigating how GAs can be mixed with other AI approaches, GA applicability to larger datasets,

关键词： Genetic algorithms Adaptive learning Real-time systems Heuristic algorithms Education Adaptation models Recommender systems Adaptive systems Systematic literature review computer science

来源：评论

学校读者我要写书评

暂无评论

DECLARATIVE NETS THAT ARE EQUILIBRIUM MODELS 10

DECLARATIVE NETS THAT ARE EQUILIBRIUM MODELS

引用

10th International Conference on learning Representations, ICLR 2022

作者： Tsuchida, Russell Yong, Suk Yee Armin, Mohammad Ali Petersson, Lars Ong, Cheng Soon Data61 CSIRO Canberra Australia Space & Astronomy CSIRO Epping Australia Machine Learning & Artificial Intelligence Future Science Platform

Implicit layers are computational modules that output the solution to some problem depending on the input and the layer parameters. Deep equilibrium models (DEQs) output a solution to a fixed point equation. Deep declarative networks (DDNs) solve an optimisation problem in their forward pass, an arguably more intuitive, interpretable problem than finding a fixed point. We show that solving a kernelised regularised maximum likelihood estimate as an inner problem in a DDN yields a large class of DEQ architectures. Our proof uses the exponential family in canonical form, and provides a closed-form expression for the DEQ parameters in terms of the kernel. The activation functions have interpretations in terms of the derivative of the log partition function. Building on existing literature, we interpret DEQs as fine-tuned, unrolled classical algorithms, giving an intuitive justification for why DEQ models are sensible. We use our theoretical result to devise an initialisation scheme for DEQs that allows them to solve kGLMs in their forward pass at initialisation. We empirically show that this initialisation scheme improves training stability and performance over random initialisation. © 2022 ICLR 2022 - 10th International Conference on learning Representationss. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Comparative Analysis of Time Series Forecasting Models for Weather Prediction: ARIMA vs. STL 8

Comparative Analysis of Time Series Forecasting Models for W...

引用

8th IEEE International Conference on Computing, Communication, Control and Automation, ICCUBEA 2024

作者： Kamble, Aahash Belsare, Sanika Chaudhari, Purva Gourshettiwar, Palash Gundewar, Swapnil Datta Meghe Institute of Higher Education and Research Department of Artificial Intellegence and Data Science Wardha India Department of Artificial Intellegence and Data Science Maharashtra Wardha India Datta Meghe Institute of Higher Education and Research Department of Computer Science and Medical Engineering Wardha India Datta Meghe Institute of Higher Education and Research Department of Artificial Intellegence and Machine Learning Wardha India

ISBN: (纸本)9798350391770

This research compares two well-known models for predicting weather: ARIMA (Auto Regressive Integrated Moving Average) and STL (Seasonal-Trend Decomposition using Loess). Accurate weather forecasts are crucial for businesses and daily life, making strong forecasting methods necessary. ARIMA finds linear patterns and time dependencies in data, while STL splits time series into seasonal, trend, and random parts. Using real-world weather data, we train and test these models. We compare their performances using MSE (Mean Squared Error) and R2 (R-squared) metrics. The research demonstrates that the STL model performs better than the ARIMA model at accurately predicting weather patterns and fitting to the data. This superior performance makes the STL model a more dependable choice for weather forecasting. This study enhances techniques for weather prediction and offers valuable information to those making decisions in weather-sensitive businesses. © 2024 IEEE.

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

An Optimized Elliptical Curve Cryptography based Crypto-Watermarking Model in Smart Healthcare Application 2

An Optimized Elliptical Curve Cryptography based Crypto-Wate...

引用

2nd International Conference on Data science and Information System, ICDSIS 2024

作者： Murthy, G. N. Keshava Manjula, G. Harshitha, P. Achyutha Prasad, N. Siddaganga Institute Of Technology Department Of Electronics And Instrumentation Engineering Karnataka Tumakuru India Bgs College Of Engineering And Technology Department Of Cse Bangalore India Nitte Meenakshi Institute Of Technology Artificial Intelligence And Machine Learning Bengaluru India East West Institute Of Technology Department Of Computer Science And Engineering Bengaluru India

ISBN: (纸本)9798350381665

Telemedicine uses current communication and information technology to provide clinical treatment remotely. Given the ubiquitous usage of DWT and DCT are used for watermarking, ECC-FFA is used for encryption. The only cryptographic algorithms used in the current approaches for watermarking are AES, DES, and RSA, and the DCT and DWT are typically used separately. But because we integrated the ECC-FFA cryptographic method with the DWT and DCT watermarking technologies, the recommended solution is more effective than earlier ones.. A strong and lossless patient medical information exchange system employing crypto-watermarking is suggested in order to secure medical data. For the watermarking approximate, the discrete wavelet alter (DWT) and discrete cosine alter (DCT) are combined, and the elliptical curve cryptography (ECC) algorithm is utilized. At the same time, metaheuristic algorithms may be used to solve the optimum key creation issue in cryptography, which is viewed as an optimisation challenge. As a stem, the master nucleus of this masterpiece is on the development of cryptographic encryption for picture security based on metaheuristic optimization algorithms. According to this perspective, this study creates the ECC-FFA model, an effective produce fruit fly optimisation (FFO) technique with ECC for picture protection. The suggested model uses the ECC technique to carry out the encryption and decryption procedure. Various medical photos were used in the experiment, and the peak signal to noise ratio was used to assess how well the suggested method worked. © 2024 IEEE.

关键词： Optimization

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：