检索结果-内蒙古大学图书馆

computer science and Emerging Technologies (CSET), International Conference on

作者： S.A. Sahaaya Arul Mary Akshaj Nevgi Rhea Ranjith Nair Jehan Sharukh Bhathena Angad Chaudhry S. Sharon Jessika School of Computer Science and Engineering VIT Computer Science and Engineering Computer Science with specialization in Data Science

Cloud computing is a technology that allows the utilisation of a vast network of computers that are distributed and run in parallel with one another. The management of the multimedia files presents challenges and the significant of which is the prevalence of attackers and users with malicious intent. This article presents the conceptual foundation for a four-tiered data security paradigm that can be implemented in cloud computing. The proposed framework employs a DNA-computing-based password or secret key with a length of 1024 bits for the purpose of encrypting the user private multimedia file or correspondence. The DNABMS algorithm is applied in the cryptographic generation of digital identities as well as pseudorandom number generators. The results of the testing that was done on the model have validated both its reliability and its efficacy, demonstrating that the model that was developed is both reliable and effective. Experiments have demonstrated that the developed method is superior to other well-known existing strategies in terms of both effectiveness and efficiency.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Intelligent E-Commerce Chatbot for Personalized Product Recommendations Using Text Mining and Machine Learning

Intelligent E-Commerce Chatbot for Personalized Product Reco...

引用

Advances in Computation, Communication and Information Technology (ICAICCIT), International Conference on

作者： M.S. Minu Adithya Kavya SreeRanjini Department of Computer Science and Engineering SRM Institute of Science and Technology Ramapuram Chennai India Department of Computer Science and Engineering with Specialization in Big Data Analytics SRM Institute of Science and Technology Ramapuram Chennai India

ISBN: (数字)9798331541217

ISBN: (纸本)9798331541224

Innovative technology solutions have been developed in response to the growing need for effective and customized client contact on e-commerce platforms. This work introduces an intelligent chatbot system that uses machine learning and text mining techniques to improve user satisfaction and answer customer concerns. Advanced Natural Language Processing (NLP) models have been trained on large datasets, allowing for precise user intent interpretation and pertinent product recommendations. A strong recommendation engine is included into the system architecture to aid in decision-making, ultimately enhancing the customer experience by providing individualized, real-time help. The study also highlights the significance of data privacy by using privacy-preserving techniques to safeguard user data. The system’s scalability and performance benefits are highlighted through thorough comparisons with current models. By showcasing the useful uses of machine learning and text mining in enhancing customer contact and service delivery, this study makes a substantial contribution to the development of AI-driven solutions in e-commerce.

关键词： Text mining Machine learning algorithms Scalability Systems architecture Machine learning Chatbots User experience Real-time systems Electronic commerce Time factors

来源：评论

学校读者我要写书评

暂无评论

Customized Movie Recommendation for Enhanced Entertainment

Customized Movie Recommendation for Enhanced Entertainment

引用

Cybernation and Computation (CYBERCOM), International Conference on

作者： M.S. Minu Srikar Talapalli Saahithi Chevuri Medhasri T.S. Department of Computer Science Engineering SRM Institute of Science And Technology Ramapuram Chennai India Department of Computer Science Engineering with Specialization in Big Data Analytics SRM Institute of Science and Technology Ramapuram Chennai India

ISBN: (数字)9798331542344

ISBN: (纸本)9798331542351

The surging popularity of online movie databases has created a challenge for viewers: choosing a film from a massive library can be overwhelming. In this paper, it proposes to design a new hybrid movie recommendation powered by machine learning techniques as a solution to improve user experience. Among those techniques, two are combined into this paper: content-based filtering, using the real features of a movie such as genre and a director, and collaborative filtering, which uses the rating provided by users. This hybrid approach thus improves the intrinsic weaknesses that reside in both these methods individually. On the other hand, content-based filtering tends to reduce exploration to movies of the exact type one is doing well at, whereas, inversely, collaborative filtering settings often mean that a user will be exposed only to films within his or her already-recognized taste profile. It is expected that the proposed hybrid system will solve both problems by balancing this line between exploring familiar cinematic territory and making new recommendations based on both user preferences and the entire collective intelligence of the user base. The approach would aim to enrich user satisfaction by facilitating the selection of movies and providing a richer and more diversified movie-viewing experience.

关键词： Hands Filtering Collaborative filtering Transforms Machine learning Motion pictures User experience Libraries Hamming distances Recommender systems

来源：评论

学校读者我要写书评

暂无评论

Machine Learning Model for Sentimental Analysis of Amazon Reviews

Machine Learning Model for Sentimental Analysis of Amazon Re...

引用

Electronic Systems and Intelligent Computing (ICESIC), International Conference on

作者： A. Umamageswari R.J. Pratishwaran M. Poojitha Reddy R. Yuvan Sankar Raj Department of Computer Science and Engineering SRM Institute of Science and Technology Ramapuram Chennai India Department of Computer Science and Engineering With Specialization in Big Data Analytics SRM Institute of Science and Technology Ramapuram Chennai India

ISBN: (数字)9798331522988

ISBN: (纸本)9798331522995

The goal of this project is to draw a deeper understanding of the subjective nature behind online product reviews, largely by examining a large dataset received from Amazon that contains numerous star ratings and comments. Since there is such a massive amount of data on the Amazon platform, it was perfect for the analysis. Our methodology is platform-agnostic and can be easily extended to other comparable datasets from other web platforms with comparable guarantees in achieving wide applicability. Our primary motivation is improving the dependability of online shopping. Since product reviews are currently widely used by many consumers as guides in making decisions to buy products, such reviews ought to be fair representations of the actual dependability and quality of the products. The goal of our effort is to identify patterns in the language and ratings of such reviews that would directly reflect the real customer sentiment and also the reliability of the product. Our approach has yielded already a rate of about 92%, which shows it has the potential greatly to raise the legitimacy of online reviews. We'd like to make our customers feel more confident and better equipped with information to make better and safer purchases on a website like Amazon and others. In the final analysis, we strive to make online shopping for our customers worldwide safer and more trustworthy.

关键词： Analytical models Sentiment analysis Reviews Stacking Stars Predictive models Boosting Ensemble learning Electronic commerce Random forests

来源：评论

学校读者我要写书评

暂无评论

Fast Moving Consumer Goods Object Detection Using YOLOV8

Fast Moving Consumer Goods Object Detection Using YOLOV8

引用

Electronic Systems and Intelligent Computing (ICESIC), International Conference on

作者： A. Umamageswari Mukund. P.U Abhishek. V.B Y. Devi Vaishnavi Department of Computer Science and Engineering SRM Institute of Science and Technology Ramapuram Chennai India Department of Computer Science and Engineering With Specialization in Big Data Analytics SRM Institute of Science and Technology Ramapuram Chennai India

ISBN: (数字)9798331522988

ISBN: (纸本)9798331522995

The basis of this project is to investigate whether the YOLO, an object detection algorithm where 'You Only Look Once' constitutes the name, could be applied to develop FMCG management; together with the management of FMCG, it becomes the gateway to increasing retail precision, efficiency, and agility. Under real-time processing, the system detects and counts FMCG products on retail shelves with an accuracy rate of 92.5%. This accuracy ensures that the optimum stock levels are maintained and there will be no discrepancies. The system processes video feeds at 0.08 seconds per frame, thus allowing inventory data to be updated in real-time to enable quick, data-driven decisions. YOLO's flexibility ensures consistent performance across different store layouts and product types. This system integrates with other retail management tools and allows integrating inventory data in the real time. This means that it would be made available with invaluable insights which would prevent stock depletion while helping to curtail costs. This project takes YOLO ahead of just being a game changer in the FMCG inventory management while operating to reduce expenses and customer satisfaction due to product availability.

关键词： YOLO Training Accuracy Scalability Refining Streaming media Logic gates Real-time systems Mobile handsets Monitoring

来源：评论

学校读者我要写书评

暂无评论

Image Captioning with Audio Reinforcement using RNN and CNN

Image Captioning with Audio Reinforcement using RNN and CNN

引用

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

作者： Rohan Patankar Harshik Sethi Aditi Sadhukha Nishant Banjade Ashwini Mathur Department of Computer Science and Engineering specialization in Data Science Jain University Bengaluru India Department of Computer Science and Engineering Jain University Bengaluru India

Image captioning involves generating a descriptive text that encapsulates the visual information contained in an image. This ppt proposes a deep learning model for image captioning that utilizes a Vision Transformer (ViT) and a GPT-2 network. Specifically, the ViT is employed to extract image features, which are then used by the GPT-2 network to generate captions for the images. To evaluate the effectiveness of the model, experiments are conducted on a Stanford dataset comprising images and their corresponding captions, and demonstrate that our model achieves performance comparable to other state-of-the-art image captioning models. Proposed results suggest that our model has the potential to generate accurate and semantically meaningful captions for images, and could be useful for various applications such as improving the accessibility of visual media.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Youth Unemployment Mitigation: Leveraging Machine Learning and Exploratory data Analysis for Evidence-Driven Strategies

Youth Unemployment Mitigation: Leveraging Machine Learning a...

引用

Engineering Informatics, IEEE

作者： S. Aarthi Dharmita A Pragathi G S Elakkiya Dept. of Computer Science Engineering SRM Institute of Science and Technology Chennai India Dept. Computer Science Engineering specialization with Big Data Analytics SRM Institute of Science and Technology Chennai India

ISBN: (数字)9798350338522

ISBN: (纸本)9798350338539

Youth unemployment represents an urgent global socioeconomic challenge. This study combines machine learning and exploratory data analysis to understand and solve this problem comprehensively. Traditional approaches often rely on qualitative assessments and historical data requiring a data-driven transition to more effective solutions. Our approach integrates machine learning algorithms and Exploratory data Analysis techniques to analyze diverse data sets, identify influencing factors, and recommend targeted interventions. The analysis process includes data collection, preprocessing, feature selection, machine learning modeling, and Exploratory data Analysis techniques to understand the dynamics of the Better understanding unemployment among young people. Preliminary results reveal precise predictive patterns and previously unrecognized relationships, providing evidence-based solutions to inform policy and support the economic well-being of younger generations. Further research and validation are needed to increase applicability.

关键词： Technological innovation Renewable energy sources data analysis Machine learning algorithms Wind energy Machine learning Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Windmill Pitch Prediction And Error Correction With Adaptive Control And Current Generation Analysis Using data Analysis

Windmill Pitch Prediction And Error Correction With Adaptive...

引用

Energy, Materials and Communication Engineering (ICEMCE), International Conference on

作者： M. S. Minu Rohit Suryaa S Jovan Titus J Sharan S Dept. of Computer Science Engineering SRM Institute of Science and Technology Chennai India Dept. Computer Science Engineering Specialization With Big Data Analytics SRM Institute of Science and Technology Chennai India

The growing prominence of wind energy as an eco-friendly power alternative amplifies the need for optimal turbine performance. Central to this is the ability to accurately predict and modulate the wind turbine pitch. Our research focuses on integrating adaptive control strategies with advanced power generation analytics to enhance pitch prediction precision. We have processed and analyzed vast amounts of wind data using state-of-the-art data analytics to discern patterns in wind velocity changes accurately. The continuous stream of real-time data is the backbone of our adaptive controls, ensuring perpetual pitch adjustments that optimize energy capture. In tandem with this, we present a thorough analysis linking momentary wind shifts to power production, ensuring consistent and efficient power output. The culmination of these methodologies offers a breakthrough solution in wind energy optimization. Preliminary results highlight the paramount importance of real-time data analytics in revolutionizing green energy advancements.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Real-Time Pothole Detection at night to prevent road accidents using YOLOV5

Real-Time Pothole Detection at night to prevent road acciden...

引用

International Conference on Recent Trends in Advance Computing (ICRTAC)

作者： Gouranga Mandal Anurag De Arindam Dey Sudeepthi Gangarapu Sharmila Rani Chekuru Chekuri Nandini School of Computer Science and Engineering Vellore Institute of Technology Andhra Pradesh India School of Computer Science and Engineering With Specialization in Data Analytics Vellore Institute of Technology Andhra Pradesh India

This article proposes a technique to create a pothole detection system that can operate both during the day and at night. This model was developed using the real-time object identification YOLO (You Only Look Once) technique. The potholes are located using a pre-trained model with YOLO v5. In its creation, the PyTorch framework is utilized. The first YOLO model created using the PyTorch framework is YOLOv5, which is a lot more user-friendly and lightweight. In a manner similar to real-time object detection systems, the proposed method displays potholes in real time and emphasizes them with boundary boxes for accurate identification. The accuracy achieved with this method is 97% during the day and 92% at night which is found to be satisfactory.

关键词：

来源：评论

学校读者我要写书评

暂无评论

THE NAVAL SHIP RESEARCH AND DEVELOPMENT CENTER ADVANCED STRUCTURE FACILITYxs

引用

Naval Engineers Journal 1973年第1期85卷 43-49页

作者： BECKER, LOUIS A. SIEGRIST, FRANKLIN I. Louis A. Becker was born in New Rochelle N.Y. in 1930 receiving his earlier education in the New Rochelle Public Schools. He completed his undergraduate studies at Manhattan College in 1952 receiving his BCE degree during which time he was also engaged in land surveying. Following this he did postgraduate study at Virginia Polytechnic Institute obtaining his MS in 1954. He joined Naval Ship Research and Development Center in 1953 as a Junior Engineer and is currently the Head of the Engineering & Facilities Division Structures Department. His field of specialization is Structural Research and Development. Franklin I. Siegrist was born in Knoxville Tenn. in 1937 receiving his earlier education in the Public Schools of Erie Pa. He attended Pennsylvania State University graduating in 1962 with a Bachelor of Science degree in Electrical Engineering having prior to that time served four years in the U. S. Navy. He was a Junior Engineer in the AC Spark Plug Division of General Motors from 1962 until 1964 at which time he came to the David Taylor Model Basin as an Electrical Engineer in the Industrial Department. He is currently Supervisory Engineer for Electrical and Electronics Engineering Structures Department Naval Ship Research and Development Center. His field of specialization is Electrical Engineering Control Systems Data Collection Systems Computer Applications to Structural Research and Hydraulic System Design. In the last of these he holds Patent Rights on a “Hydraulic Supercharge and Cooling Circuit” granted in 1970.

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：