检索结果-内蒙古大学图书馆

4th International Conference on Sentiment Analysis and Deep Learning, ICSADL 2025

作者： Swathi, D. Susmetha, K. Sreeji, S. Mangairkarasi, S. B.E Computer Science and Engineering with Data Science Sathyabama Institute of Science and Technology Semmancheri TamilNadu Chennai600119 India Sathyabama Institute of Science and Technology Semmancheri Department of Computer Science and Engineering TamilNadu Chennai6001109 India

ISBN: (纸本)9798331523923

The Sign Language Recognition System has b.en designed to capture video input, process it to detect hand gestures, and translate these gestures into readab.e text. The project consists of several key components and steps: Video Processing: Using OpenCV, the system captures frames from the video input. MediaPipe processes these frames to detect and track hand landmarks in real time. OpenCV capabilities allow for efficient frame extraction and basic image processing tasks such as resizing and normalization. Hand Detection and Tracking: MediaPipe pre-trained models identify and track hand movements within the video frames. The accurate detection and tracking of the hand movements are critical for the sub.equent recognition of the sign language gestures. Sign Language Recognition: The core system is the deep learning model, trained using the TensorFlow and Keras on a dataset of sign language gestures. The model learns to classify the detected hand movements into corresponding sign language characters or words. Convolutional Neural Networks (CNNs) are typically used for task due to their effectiveness in image recognition tasks. Text Display: Once the system recognizes the signs, it converts them into text and displays the output. This can be done through a console output or a graphical user interface (GUI) built with Tkinter. The GUI provides a user friendly experience, allowing users to see the translated text in real-time. © 2025 Ieee.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Identification of Therapeutic Plants Using Machine Learning 2

Identification of Therapeutic Plants Using Machine Learning

引用

2nd International Conference on emerging Trends in Information Technology and engineering, ic-eTITe 2024

作者： Rohini, S. Keerthana Shree, M.U. Jayalakshmi, R. Malathi, M. Jabasheela, L. Panimalar Engineering College M.E Computer Science and Engineering Tamil Nadu Chennai India Panimalar Engineering College B.E Computer Science and Engineering Tamil Nadu Chennai India Panimalar Engineering College Dept of Computer Science and Engineering Tamil Nadu Chennai India Panimalar Engineering College Department of Computer Science and Engineering Tamil Nadu Chennai India

ISBN: (纸本)9798350328202

It takes a lot of work to develop a computerized method for classifying plants for medicinal purposes. There are countless kinds of plants found in India, and each one has its own unique set oftherapeutic advantages. background information is necessary for manual identification and categorization because it is difficult for people to recall the proper titles of all plant species and their *** is crucial to preserve these medicinal plants since doing so will benefit several industries, including medicine, botanical research, and taxonomic studies, among others. Current technology cannot match thediversity of medicinal herb species that existin India. Utilizing textural traits that are crucial for recognizing and classifying leaves, the recommended technique makes itsimpler to categorize medicinal plants. The feature extraction, categorization, and picture enhancement stages are the three main components of the suggested method. The qualities that could be matched betweenthe leaf images were gathered using digital image processing methods after cell phones were used to snap the leaf photos. The CNN classifier is then used to create a machine learning classifier. © 2024 Ieee.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

enhancing Credit Card Security: A Machine Learning Approach for Fraud Detection 7

Enhancing Credit Card Security: A Machine Learning Approach ...

引用

2023 7th International Conference On Computing, Communication, Control And Automation, ICCUbeA 2023

作者： Karkhile, Komal Raskar, Sanskruti Patil, Rachana bhangare, Vaibhav Sarode, Atharva Pimpri Chinchwad College of Engineering B.E Computer Engineering Pune India Pimpri Chinchwad College of Engineering Pune India

ISBN: (纸本)9798350304268

Transactions increase in frequency as the world swiftly adopts digitisation and a cashless economy. The use of credit cards has dramatically increased in recent years. Financial institutions face a large loss as a result of the expanding related fraud activities. As a result, we must evaluate transactions to determine which are real and which are fraudulent. In this essay, we present a comprehensive study of the various methods for detecting credit card fraud. These methods make use of bayesian belief Networks, algorithms, Decision Trees, Logistic Regression, Genetic Random Forests, Markov Models, and Hidden Support Vector Machines (SVM). There is a thorough examination of several approaches offered. Following analysis, we put the SVM and LR models into practice, along with addressing data imbalances and feature extraction. We summarise the advantages and disadvantages of the same as stated in the respective publications as our conclusion to the paper. We want to use a credit card approach that is effective. © 2023 Ieee.

关键词： Adaboost ANN Credit Card Fraud Detection DT Fraud transaction GA KNN LR Machine Learning Nb RF SMOTe SVM

来源：评论

学校读者我要写书评

暂无评论

brain Tumor Detector Using SVM Algorithm 1

Brain Tumor Detector Using SVM Algorithm

引用

1st International Conference on Computational science and Technology, ICCST 2022

作者： Aravintharaj, S. Mithileshan, M. Priya, b. B.E Computer Science Engineering Sri Sairam Engineering College Tamil Nadu Chennai India Sri Sairam Engineering College Computer Science Department TamilNadu Chennai India

ISBN: (纸本)9781665476553

In the healthcare sector, disease prediction must be extremely precise to allow for early, effective treatment. Our overall purpose is to use a machine learning model to predict brain tumour's at an early stage. The brain is the most crucial organ of the human body since it regulates the operation of all other organs and aids in decision-making. It is basically the central nervous system's command post and is in charge of carrying out the body's regular voluntary and involuntary functions. The tumour is an uncontrolled proliferation of undesirab.e tissue that has formed a fibrous mesh inside of our brain. The primary goal is to use this study to detect brain tumours at an initial stages. The study would provide a forecast indicating whether a tumour is present or not. This tool can be used as a significant asset to any medical facility dealing with brain Tumor. Using machine learning and deep learning algorithms enab.es the detection of brain tumour's. We use the algorithm Support Vector Machine (a supervised machine learning approach that can be utilized for both regression and classification prob.ems issues) out of all the machine learning algorithms since it has a greater precision and is simple to train on big datasets. In this study, the histogram of oriented gradient is used to collect the feature information from medical pictures of patients tumour's stored within the database. SVM is then used to separate these photos into tumour and non-tumor pictures. by using this method, it is possib.e to predict brain tumour's quickly and with a high degree of accuracy (95%), which aids in patient treatment. © 2022 Ieee.

关键词： Tumors

来源：评论

学校读者我要写书评

暂无评论

Detection and Categorization of Conflict Flows Within SDN environments using Machine Learning Approach 2

Detection and Categorization of Conflict Flows Within SDN En...

引用

2nd International Conference on emerging Trends in Information Technology and engineering, ic-eTITe 2024

作者： Kousalya, S. Sundararajan, Kanthimathi Vasudevan, I. Jaichitra Sheela, L. Jaba Thyagarajan, Sarunya Panimalar Engineering College M.E. Computer Science and Engineering Tamil Nadu Chennai India Panimalar Engineering College B.E. Computer Science and Engineering Tamil Nadu Chennai India Panimalar Engineering College Dept of Computer Science and Engineering Tamil Nadu Chennai India

ISBN: (纸本)9798350328202

Software-Defined Networking (SDN) is known for its remarkab.e versatility and adaptability. SDN applications encompass a wide range of network management and control functionalities, including load balancing, access control, and routing. However, SDN can encounter issues stemming from conflicting traffic patterns that may degrade network performance in relation of efficiency and optimization. These conflicts arise when factors such as priority and action settings are adjusted. Furthermore, IP spoofing, commonly employed for anonymity and amplification, frequently leads to widespread distributed denial-of-service (DDoS) attacks. We've established a sufficient condition based on the duration and frequency of DDoS attacks. Notably, our sophisticated attack method generates legitimate traffic within the SIP network using reflection techniques. 'As a result, it has the ability to bypass security measures such as blacklists, IP blocking, rate limiting based on packet counts or session/transaction volumes, and automated systems designed to detect unnatural message generation. These security mechanisms are commonly employed in advanced security setups, but the system or technique in question can effectively avoid detection or restriction when interacting with digital environments.' © 2024 Ieee.

关键词： Network security

来源：评论

学校读者我要写书评

暂无评论

Image Super-Resolution Using Auto encoders

Image Super-Resolution Using Auto Encoders

引用

International Conference on Trends in electronics and Informatics (ICeI)

作者： K. Sandhya Rani Pancheti bhavya R. Vignesh e. Murali D. Deepa J. Cruz Antony B.E Computer Science and Engineering Sathyabama Institute of Science and Technology Chennai Tamil Nadu India Department of Computer Science and Engineering Sathyabama Institute of Science and Technology Chennai Tamil Nadu India

ISBN: (数字)9798331544607

ISBN: (纸本)9798331544614

Image super-resolution (SR) remains a crucial prob.em in computer vision to obtain high resolution images from low-resolution ones. In this paper, a novel approach towards SR is presented with the help of auto-encoders, a specific kind of neural network whose task is to learn compressed representations of the high resolution images. In the context of the proposed model, there is an encoder, which, alternately, compresses the input and a decoder which reconstruct the output is proposed as capturing as well as reproducing all the details of an image. experimental results show that the proposed method is one of the most efficient and accurate ones on benchmark datasets in terms of better details preservation and artefact reduction besides reducing processing time compared to the conventional methods. This makes this approach to be flexib.e and efficient to be used in medical imaging, satellite and digital photography making it an effective solution to improving image quality and resolution.

关键词： Image quality computer vision Visualization Image coding Superresolution Neural networks Signal processing algorithms Signal processing Optical flow Image reconstruction

来源：评论

学校读者我要写书评

暂无评论

An Integrated Approach to Robotic Ob.ect Grasping and Manipulation

arXiv

引用

arXiv 2024年

作者： Ahmed, Owais Huzaifa, M. Areeb, M. Khan, Hamza Ali Students B.E Computer & Information System Engineering NED University OF Engineering and Technology Karachi Pakistan

In response to the growing challenges of manual labor and efficiency in warehouse operations, Amazon has embarked on a significant transformation by incorporating robotics to assist with various tasks. While a substantial number of robots have b.en successfully deployed for tasks such as item transportation within warehouses, the complex process of ob.ect picking from shelves remains a significant challenge. This project addresses the issue by developing an innovative robotic system capab.e of autonomously fulfilling a simulated order by efficiently selecting specific items from shelves. A distinguishing feature of the proposed robotic system is its capacity to navigate the challenge of uncertain ob.ect positions within each bin of the shelf. The system is engineered to autonomously adapt its approach, employing strategies that enab.e it to efficiently locate and retrieve the desired items, even in the ab.ence of pre-established knowledge about their placements. Crucially, the robotic system operates with a paramount emphasis on autonomy. The intricate interplay of algorithms, control mechanisms, and sensor fusion empowers the robot to execute the entire ob.ect picking task without human intervention. This unfaltering commitment to autonomy is a pivotal step towards revolutionizing warehouse operations, potentially paving the way for unprecedented levels of efficiency and productivity. This project serves as a testament to the intersection of robotics, computer vision, and artificial intelligence in tackling a complex challenge within the realm of modern logistics. The envisioned robotic system represents a significant advancement in autonomous ob.ect picking technology, holding the promise of transforming conventional warehousing practices. As the fusion of cutting-edge technology and logistical innovation unfolds, the outcomes of this endeavor have the potential to redefine the future of warehouse operations and automation within the industry. © 2024, CC bY.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Private Document Vault with Server-Side encryption in Cloud AWS S3 bucket

Private Document Vault with Server-Side Encryption in Cloud ...

引用

International Conference on Communication and electronics Systems (ICCeS)

作者： Daliparthi Jeevana Aditya Sunki Laxmanraj R. Sathya bama Krishna Computer Science Engineering (B.E) Sathyabama Institute of Science and Technology Sath Sathyabama Institute of Science and Technology

The most requested future-oriented innovation in the world is distributed computing. Distributed storage is one of the most famous managements presented in cloud computing. Information is stored on various external servers as opposed to the fixed servers used in traditionally located information capacity in distributed storage. All the information stored on various external servers leaves the client unattended, and no one knows exactly where the information is stored. Rejected by distributed storage vendors who claim they can protect your information, but no one trusts them. Information stored via the cloud and traveling in cleartext design within an organization is a security risk. This research study proposes a strategy for allowing clients to securely store and access information from distributed stores. This technology ensures the security and protection of information stored in the cloud. Another advantage of this strategy is that it is encrypted using cryptographic methods. In this technology, the files are encrypted using both symmetric and asymmetric algorithms, which is nothing but Hybrid encryption and as a result the end user will get a pair of keys that will help in decrypting the files. If a data b.each occurs the first layer of security will get damaged but the second layer of security helps in saving the files from data b.each.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Framework for Video based Sign Language Interpretation Using Machine Learning and Statistical Methods

A Framework for Video Based Sign Language Interpretation Usi...

引用

Sentiment Analysis and Deep Learning (ICSADL), International Conference on

作者： Swathi D Susmetha K Sreeji. S S. Mangairkarasi B.E Computer Science and Engineering with Data Science Sathyabama Institute of Science and Technology Semmancheri Chennai TamilNadu India Department of Computer Science and Engineering Sathyabama Institute of Science and Technology Semmancheri Chennai TamilNadu India

ISBN: (数字)9798331523923

ISBN: (纸本)9798331523930

关键词： Hands Deep learning Sign language Translation Tracking Text recognition Speech recognition Streaming media Real-time systems Graphical user interfaces

来源：评论

学校读者我要写书评

暂无评论

blockchain and Federated Reinforcement Learning for Vehicle-to-everything energy Trading in Smart Grids

IEEE Transactions on Artificial Intelligence

引用

Ieee Transactions on Artificial Intelligence 2024年第2期5卷 839-853页

作者： Moniruzzaman, Md Yassine, Abdulsalam benlamri, Rachid Department of Electrical and Computer Engineering Lakehead University Thunder BayONP7B 5E1 Canada Department of Software Engineering Lakehead University Thunder BayONP7B 5E1 Canada University of Doha for Science and Technology Doha24449 Qatar

The proliferation of electric vehicles (eVs) and the advancement of vehicle-to-everything energy trading systems are expected to play a crucial role in alleviating the stress on the electric grid during peak hours. However, the wide adoption of these paradigms requires intelligent mechanisms that protect the security and privacy of eV users. This article proposes a novel federated reinforcement learning system combined with blockchain technology to maximize eV users' utility while preserving the security and privacy of trading transactions. Furthermore, we develop the concept of proof of state of charge as a consensus mechanism to determine the winning eVs and reward them as block miners in the blockchain. The proposed system is validated through comprehensive simulation experiments utilizing a real-world dataset. The model is implemented on the Avalanche blockchain platform to demonstrate its real-world feasibility. The test results show that the proposed scheme improves eV users' utility significantly compared to the existing studies. The obtained simulation results indicate the effectiveness and robustness of the proposed system. © 2023 Ieee.

关键词： Reinforcement learning

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：