检索结果-内蒙古大学图书馆

5th IEEE International Conference on Computing, Power, and Communication Technologies, IC2PCT 2024

作者： Julian, Anitha Maheswar, Challa Ramyadevi, R. Murali dhar, M.S. Selvi, S. Saveetha Engineering College Department of Computer Science and Engineering Chennai India Vel Tech Rangarajan Dr. Sagunthala R & D Institute of Science and Technology Department of Computer Science and Engineering Chennai India R.M.K Engineering College Department of Computer Science and Engineering Chennai India

ISBN: (纸本)9798350383522

Sales on e-commerce platforms are significantly influenced by discounts. When a discount is offered, 80% of buyers who initially show disinterest end up making a purchase, per a Retail Me-not survey. This increases revenue and draws in new clients who might not have otherwise thought about making a purchase. Another survey by Accenture reveals that 75% of consumers are more inclined to choose a brand that provides personalized discounts. To retain customers, e-commerce websites can implement tailored discount strategies based on customers' past purchases or preferences. The decision-making process for discounts involves various factors. Pricing strategies and discounts, as identified in the study, are pivotal in influencing consumer behavior and encouraging purchases, particularly among new customers. This research delves into the complexities of discounting practices and their impact on the online retail ecosystem. Employing a comprehensive methodology that combines quantitative and qualitative techniques, the study investigates the frequency, trends, and effectiveness of discounts across different e-commerce platforms. Through extensive data collection, including details on discount percentages, durations, and consumer feedback, the research aims to reveal insights into the strategic implementation of discounts. The study's main objective is to analyze discounts that are given on a variety of products by gathering information from an online store and using the characteristics, reviews, and ratings of the products as factors to calculate the discount value. © 2024 IEEE.

关键词： data analysis discount analysis EdA estimation techniques feedback and reviews predictive modelling

来源：评论

学校读者我要写书评

暂无评论

Invoice Processing Automation Using UI Path Studio 5

Invoice Processing Automation Using UI Path Studio

引用

5th IEEE International Conference on Computing, Power, and Communication Technologies, IC2PCT 2024

作者： Ramyadevi, R. Anbuselvan, A. Julian, Anitha Selvi, S. Murali dhar, M.S. Saveetha Engineering College Department of Computer Science and Engineering Chennai India R.M.K Engineering College Department of Computer Science and Engineering Chennai India Vel Tech Rangarajan Dr. Sagunthala R & D Institute of Science and Technology Department of Computer Science and Engineering Chennai India

ISBN: (纸本)9798350383522

Invoices are the fundamental document that play a vital role in encapsulating the details of the products and the business transactions between the seller and the buyer. We cannot check our invoices at any time for emergencies. Substituting the case, by storing the basic details of multiple invoices in an excel sheet might be used for future purposes. This paper provides the advancement of data extraction through automation technologies. We begin this research by the technique Optical Character Recognition (OCR) in automation of data extraction from invoices. This reduces the manual errors during extraction as the entire process works with the automation and provides an accuracy of 95%. The paper discusses the design of the automation that has to be processed for the data extraction including the invoice details, line items and relevant metadata and stored in a structured and accessible format. This storage allows the customer to get through all their product details in a document. Furthermore, the study investigates the integration of extracted data from the invoice to the customer. This integration acts as the strategic role in transforming invoice data into a dynamic asset, enabling customers to glean insights. The paper incorporates real-world examples and case studies to illustrate implementations of scrapping techniques using automation. By addressing challenges such as technological limitations, integration complexities, and data security concerns, the paper provides practical understanding for customers in processing the automation. © 2024 IEEE.

关键词： Accuracy Automation Technologies data Extractions data Storage Invoice Processing Optical Character Recognition (OCR)

来源：评论

学校读者我要写书评

暂无评论

Anomaly detection using deep learning approach for IoT smart city applications

引用

Multimedia Tools and Applications 2025年第17期84卷 17929-17949页

作者： Shibu, S. Kirubakaran, S. Remamany, Krishna Priya Ahamed, Suhail Chitra, l. Kshirsagar, Pravin R. Tirth, Vineet Department of Electronics and Communication Engineering Panimalar Engineering College Tamil Nadu Chennai600123 India Department of Computer Science and Engineering CMR College of Engineering and Technology Telangana Hyderabad501401 India Engineering Department College of Engineereing and Technology University of Technology an Applied Sciences PC Musandam811 Oman Machine Learning Software Engineer Paragon Semvox GmbH Saarland Kirkel Germany Department of Electrical and Electronics Engineering Aarupadai Veedu Institute of Technology Vinayaka Missions Research Foundation Tamil Nadu Chennai603104 India Department of Electronics & Telecommunication Engineering J D College of Engineering & Management Maharashtra Nagpur India Department of Mechanical Engineering College of Engineering King Khalid University Asir Abha61421 Saudi Arabia

With the advancements of IoT devices, many smart applications start to rule this era. In particular, smart cities has been adapted and realized by many countries around the world. In smart cities, vas amount of data is generated at every second. This vast data need a transmission medium which could be wireless standard. However, security is the main concern in such applications since the smart transmission always binds with anomalies. The existing anomaly detection systems need improvement in accuracy due to inefficient feature extraction and selection procedure. This paper proposes an accurate anomaly detection technique that built upon deep learning approach. We proposed a Combined deep Q-learning (CdQl) algorithm for anomaly detection. Priory, optimal features are selected by using Spider Monkey Optimizer (SMO). With the optimal features, CdQl detects anomalies accurately. In addition, the CdQl algorithm learns the environment in order to monitor the network data continuously. This continuous monitoring and optimum features helps in accuracy improvement up to 98%. © The Author(s), under exclusive licence to Springer Science+Business Media, llC, part of Springer Nature 2024.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Rapid Colorimetric and Artificial Intelligence-based Methods for determining the Microbial Quality of Raw Milk, Processed Milk, and Milk Products 8

Rapid Colorimetric and Artificial Intelligence-based Methods...

引用

8th International Conference on Inventive Computation Technologies, ICICT 2025

作者： Muthusundari, S. Sreeja, Gomasani HemaSree, G.M. HemaPriya, K. Department of Computer Science and Engineering R.M.D Engineering College Tamil Nadu India Department of Computer Science and Engineering R.M.D Engineering College Tamil Nadu India

ISBN: (纸本)9798331512248

Besides maintaining the microbial quality of milk and dairy foods for food safety and public health, contamination detection by traditional methods has been slow and labor-intensive. Fast and efficient alternative methods are therefore urgently needed. This paper discusses the application of the advanced colorimetric and artificial intelligence (AI)-based approaches of assessing microbial quality in raw milk, processed milk, and different dairy products. Meanwhile, AI models such as machine and deep learning approaches analyze spectral data, images, and sensor outputs to develop accuracy and predictive capability. Therefore, the integrated approaches provide real-time, non-invasive, and economically effective means for microbial assessment, hence an advantage over conventional techniques. Experiments have illustrated that these methods can very efficiently detect microbial contamination to high confidence levels. This technique has a lot of potential in improving quality control among dairy industries for consumer safety and efficient supply chain management. © 2025 IEEE.

关键词： artificial intelligence colorimetric methods dairy products food safety machine learning Microbial quality processed milk raw milk

来源：评论

学校读者我要写书评

暂无评论

Real-Time deep learning for dynamic Scene Understanding and Autonomous Robot Navigation

Real-Time Deep Learning for Dynamic Scene Understanding and ...

引用

2024 International Conference on Cybernation and Computation, CYBERCOM 2024

作者： Muthukrishnan, A. Pushparani, S. Poongavanam, N. Arun, M. Ilangovan, S. Vel Tech Rangarajan Dr. Sagunthala R and D Institute of Science and Technology Department of Computer Science and Engineering Avadi Tamil Nadu Chennai India Meenakshi College of Engineering Department of Computer Science and Engineering Tamil Nadu Chennai600 078 India Saveetha University Department of Computer Science and Engineering Chennai India Panimalar Engineering College Department of Electronics and Communication Engineering Tamil Nadu Chennai India K.L.N.College of Engineering Department of Information Technology Sivaganga India

ISBN: (纸本)9798331542344

In this paper, a new approach in dynamic scene understanding and robot navigation especially for autonomous robots through the integration of deep learning approach with real time processing is proposed. For object recognition and its localization on the image the system uses convolutional neural networks, also semantic segmentation relies on convolutional neural networks, for autonomous navigation, the deep reinforcement learning is used. The data for the research are gathered from publicly available databases and new data captured with web-cameras and lidAR sensors installed on robots exploring the chosen scenarios. The deep learning models are for real time usage by using TensorFlow lite and the models are run on Jetson Xavier. In order to investigate object detection efficiency, scene segmentation differentiate, success rate of providing navigation and system latency, various experiments were performed inside and outside the building. The outcomes also show a high degree of 'indoor' stability and an interacting environment obstacle avoidance efficiency over real-Time system operation. While these difficulties were noticed in rural outdoor environment, the system managed to navigate in space populated with dynamic obstacles and safely avoid them even if environment conditions changed, for instance, due to wind. deep learning with sensor fusion as a solution offered accurate scene understanding to make sure that autonomous navigation is possible on both indoor and outdoor settings. Thus, the research provides valuable information on the improvement of safety and efficiency in autonomous robots for use in various industries such as self-driving cars, robots for a smart warehouse etc. © 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

An Efficient Attendance Management with deep learning

An Efficient Attendance Management with Deep Learning

引用

2024 IEEE International Conference on Computing, Semiconductor, Mechatronics, Intelligent Systems and Communications, COSMIC 2024

作者： Shivanna Hema, H.P. Janardhana, d.R. Srinivas, P.M. Sahyadri College of Engineering and Management Department of Computer Science and Engineering Mangaluru India D S Dinakar Polytechnic College Department of Electronics and Communication Engineering Shivamogga India Nitte Meenakshi Institute of Technology Department of Computer Scince and Engineering Bengaluru India

ISBN: (纸本)9798331517892

Accurate attendance recording is critical in educational institutions to ensure students' and teachers' consistency and discipline. Traditional manual attendance systems are frequently inefficient and prone to errors, such as proxy attendance and missed entries, which may impact the accuracy of attendance records. To address these challenges, an automatic attendance system that uses camera-based facial recognition technology is proposed. The latest technology records accurate attendance by taking visuals of students as soon as the class starts and comparing them to an already-existing database. Face recognition happens through human detection. The concept used here is deep learning. For students, this automated solution streamlines attendance management by ensuring that records are accurate and up to date without the need for manual entry. The system efficiently keeps track of the presence of teachers, notifying the Head of department (HOd) right away in the case of an excused absence, therefore preventing disruptions during scheduled lessons. This technology significantly increases the reliability and efficiency of attendance tracking by automating the process. Enhancing record accuracy and accountability leads to a more regulated and effective learning environment that benefits teachers and students alike. This technological method offers greater precision and oversight, leading to improved institutional administration and educational outcomes. © 2024 IEEE.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Evaluating Tip Selection Algorithms for IOTA Blockchain 4th

Evaluating Tip Selection Algorithms for IOTA Blockchain

引用

4th International Conference on Futuristic Trends in Networks and Computing Technologies, FTNCT 2021

作者： Purohit, Shreya Champaneria, Tushar Computer Engineering Department L.D. College of Engineering Gujarat Ahmedabad380015 India

ISBN: (纸本)9789811950360

IOTA blockchain is an alternative to blockchain, which is utilized for millions of devices connected to an Internet of Things network. These devices can communicate data with other devices in the form of transactions using IOTA. The IOTA tangle is the network of such devices. To complete a new transaction, tips of the tangle must be discovered, which is accomplished through the use of several tip selection methods. The process of picking two tips in the IOTA tangle to which the incoming transaction connects is known as tip selection. The study of various tip selection methods used in IOTA blockchain is described in this research, and tip selection strategies are evaluated with respect to time and varied number of node configurations using JGraphT library. Finally, a comparison of all tip selection algorithms is shown, with the adaptive random walk algorithm outperforming the others. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte ltd.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

Blockchain based Roaming fraud prevention using lSTM model in 4G lTE Network 13

Blockchain based Roaming fraud prevention using LSTM model i...

引用

13th International Conference on Cloud Computing, data Science and engineering, Confluence 2023

作者： Yamuna, S. Sakthi, U. Sai Priya, G. Shanmuga Sendhilkumar, K.S. Sri Venkateswara College of Engineering Department of Computer Science and Engineering Chennai India Meenaskshi Sundarajan Engineering College Department of Computer Science and Engineering Chennai India R.M.D Engineering College Department of Computer Science and Engineering Chennai India Vit University Vellore Department of Computer Science and Engineering India

ISBN: (纸本)9781665462631

Fraud and Identity Theft constitute for huge financial loss to the telecom industry and telecom fraud accounts for a major cause of revenue loss. Among them, roaming fraud has the highest impact over network service providers, it has also become major concern for few companies. The present paper intends to provide a solution on roaming fraud with the help of a block chain-based network, which is used as secure data storage. This technology helps in minimizing financial loss, improving trust and ensures the reduction of latency in communication between the host and visitor network service provider. This is achieved by uploading the customers service report to the blockchain network as a transaction, using Inter Planetary File System (IPFS), and the service providers act as the accounts present in the network for accessing the report. It has been verified that, when the data is present in the blockchain, any outside entity cannot tamper or get hold of the data, which is an advantage of using blockchain technology. © 2023 IEEE.

关键词： Smart contract

来源：评论

学校读者我要写书评

暂无评论

A deep learning-based early alzheimer’s disease detection using magnetic resonance images

引用

Multimedia Tools and Applications 2025年第16期84卷 16561-16582页

作者： Suchitra, S. Krishnasamy, lalitha Poovaraghan, R.J. Department of Computer Science and Engineering Vel Tech Rangarajan Dr. Sagunthala R &D Institute of Science and Technology Avadi Tamil Nadu Chennai India Department of Information Technology Nandha Engineering College Tamil Nadu Erode India Department of Information Technology Jaya Engineering College Tamil Nadu Thiruninravur Chennai India

Alzheimer’s disease (Ad) is a degenerative, chronic condition of the brain for which there is now no effective treatment. However, there are medications that can slow its development. In order to stop and control the development of Ad, earlier diagnosis of the disease is quintessential. Our proposed method’s primary objective is to establish a comprehensive model for the prior detection of Alzheimer’s disease and the categorization of distinct Ad stages. This work employs a deep learning methodology, especially CNN. The proposed approach makes use of well-known models that have already been trained to classify medical images, like the EfficentNetB7 model, by applying the transfer learning principle. In order to achieve greater accuracy, convolutional neural networks (CNNs) are frequently scaled up as new resources become available at a fixed cost throughout the construction phase. A compound coefficient is used by the CNN architecture and scaling approach, which is the foundation of the pre-trained EfficientNetB7 model, to scale the dimensions equally. This proposed EfficientNetB7 model is quicker, easier, and more effective than other pre-trained models like VGG19 and InceptionV3. The proposed model includes simple structures that have memory requirements, provide manageable time, overfitting, and low computational complexity as well as training and inference speeds. The Alzheimer’s disease Neuroimaging Initiative (AdNI) dataset was employed for a comprehensive assessment of the method proposed, utilizing well-known performance metrics including sensitivity, specificity, and accuracy. The findings revealed that the improvised results achieved the accuracy metric when compared to existing methods. The EfficientNetB7 model has been enhanced, and this model achieves a sensitivity of 98.08%, specificity-98%, accuracy-98.2%, and F-score-98.95%, for multi-class Ad stage classifications. © The Author(s), under exclusive licence to Springer Science+Business Media, llC, par

关键词： Magnetic resonance

来源：评论

学校读者我要写书评

暂无评论

detecting driver Fatigue with Python and OpenCV 10

Detecting Driver Fatigue with Python and OpenCV

引用

10th International Conference on Communication and Signal Processing, ICCSP 2024

作者： Pandi, C. Anish, T.P. Selvanayaki, S. Jagadeesan, P. Vedaraj, M. Sanjay, R. Vel Tech Multi Tech Dr.Rangarajan Dr.Sakunthala Engineering College Computer Science and Engineering Avadi India R.M.K College of Engineering and Technology Computer Science and Engineering Tamil nadu India Saveetha Engineering College Artificial Intelligence and Data Science Tamil nadu Thandalam India R.M.D Engineering College Computer Science and Engineering Tamil nadu India

ISBN: (纸本)9798350353068

Utilizing eye aspect ratio analysis and facial landmarks, the sleep detection tool is intended to detect indicators of sleepiness or drowsiness in people. By leveraging the face recognition library, the program detects and extracts facial landmarks, with a particular focus on locating the positions of the eyes. The software analyzes the eye aspect ratio (EAR), which takes into account the relative distances between particular eye landmarks, to ascertain if an individual has fully or partially closed their *** video frame capture is performed from a chosen video source, typically a webcam, allowing real-time monitoring of the user. Each frame is processed to detect and analyze the eye regions, computing the EAR values for both the left and right eyes. If the EAR falls below a predefined threshold for a consecutive number of frames, it indicates that the person's eyes are closed for an extended duration, suggesting potential drowsiness or *** enhance user safety, an alarm sound is played when the program detects drowsiness, providing an immediate alert to the individual. The alarm sound serves as an auditory cue, helping the person regain alertness and avoid potential accidents or undesired consequences. Additionally, the program displays the computed EAR on the video feed, allowing for visual feedback and monitoring of the eye aspect ratio values for debugging purposes and fine-tuning the system's *** employing this sleep detection program, various applications can benefit from its capabilities. For instance, it can be utilized in the context of drowsy driving detection systems, alerting drivers when they exhibit signs of fatigue and helping prevent accidents due to impaired driving. Moreover, the program holds potential for use in other scenarios where monitoring individuals' alertness and detecting sleep-related patterns is essential, such as workplace safety or medical *** summary, the sleep detection program employs faci

关键词： Video signal processing

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：