检索结果-内蒙古大学图书馆

8th International Conference on Information System Design and Intelligent Applications, ISDIA 2024

作者： Ashita, K. Virthi, M. Mohan Deepak, K. Sangeetha, S.K.B. Department of Computer Science and Engineering SRM University Chennai India

ISBN: (纸本)9789819748914

A digital drawing canvas called Air Canvas maps and recognizes hand gestures using media-pipe, opencv, camera, and numpy. An English alphabet’s handwritten movements are translated into text. With just a wave of the finger, the user can draw on a screen. The pen’s color can be changed by simply dragging the finger over the desired hue. We start with a blank canvas, choose the necessary colors by hand, and then draw the desired character or anything else you want. It enhances communication between people and computers. To accomplish the goal of this study, fingertip tracking and hand detection are employed. The goal of this study is to identify the alphabet that is drawn by hand over a webcam. Python and Open CV will be used to implement the system. Its main goal is to create motion-to-text converters that facilitate efficient communication. For the deaf, it serves as a communication tool. © The Author(s).

关键词： Palmprint recognition

来源：评论

学校读者我要写书评

暂无评论

SET LonDEM AN D: Towards an On Demand ETL Approach for Semantic data Warehouses 6

SET LonDEM AN D: Towards an On Demand ETL Approach for Seman...

引用

6th International Conference on Electrical engineering and Information and Communication Technology, ICEEICT 2024

作者： Bhattacharjee, Amrit Deb Nath, Rudra Pratap University of Chittagong Department of Computer Science and Engineering Chattogram Bangladesh

ISBN: (纸本)9798350385779

As the application of Semantic Web technology con- tinues to grow, conducting Online Analytical Processing (OLAP) over Semantic data Warehouses (SDW ) has become an essential task. The Extract-Transform-Load (ETL) process loads data from external sources into an SDW . Generally, OLAP operations function efficiently on static data with minimal changes over time. However, challenges arise when dealing with frequent data changes, such as prices, populations, or social media data, requiring constant updates to the SDW for query processing. Additionally, not all dimensions of the cube may be crucial for answering a query. In this paper, we propose an approach named SET LonDEM AN D , which extracts an OLAP query to determine the required data, fetches the necessary data from respective sources using the ETL pipeline, and then executes the query. This approach additionally enables data retrieval from external data endpoints and seamlessly integrates the outcomes from these external endpoints with local data sources, particularly in cases where the query is federated. We assess the performance, productivity, and quality of SET LonDEM AN D compared to a traditional ETLQ approach. © 2024 IEEE.

关键词： Semantic Web

来源：评论

学校读者我要写书评

暂无评论

Real Time Web Traffic Forecasting Using LSTM and CNN

Real Time Web Traffic Forecasting Using LSTM and CNN

引用

2025 IEEE International Students' Conference on Electrical, Electronics and computer science, SCEECS 2025

作者： Kushwaha, Manveer Sangwan, Anamika Gupta, Keshav Sharda University Department of Computer Science and Engineering Greater Noida India

ISBN: (纸本)9798331529833

A Real-Time Web Traffic Forecasting System Using Hybrid LSTM and CNN Paper Development of the real-time web traffic forecasting system uses a hybrid approach combining LSTM with Conventional Neural Networks (CNN) to forecast website visitor counts and user engagement metrics for better resource and server scalability and in turn user experience. Methodology This entails the utilization of machine learning techniques in a time series forecasting context, as well as data preprocessing to truthfully make short-term forecasts. The results proved that the hybrid model performs better than the traditional statistical models like ARIMA, and this has significant impacts on dynamic management of resources. For optimized management of loads on the server, real-time traffic forecasting of web traffic is necessary. The system exploits both linear and non-linear relationships of data and, hence, makes for better short-term predictions than do conventional ARIMA techniques. This paper describes the design, implementation, and evaluation of the hybrid model with the objective of proving its superiority over the complex patterns of web traffic. The results have been much better in terms of prediction, reduced system downtime, and increased efficiency in operational functioning-land on a road to resource optimization and proactive infrastructure management. © 2025 IEEE.

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

An IoT Based Electromyography Signal Transmission from sEMG Electrodes to Client's Server with ICT Infrastructure 10

An IoT Based Electromyography Signal Transmission from sEMG ...

引用

10th International Conference on Advanced Computing and Communication Systems, ICACCS 2024

作者： Pavithra, P.M. Balakrishnan, M. Anandaraj, A. Ramya, M. Sudharsan, R. Raja Sri Shanmugha College of Engineering and Technology Department of Artificial intelligence and Data Science Salem India Dr. Mahalingam College of Engineering and Technology Department of Artificial intelligence and Data Science Pollachi India Sri Eshwar College of Engineering Department of Computer Science and Engineering Coimbatore India Sri Shanmugha College of Engineering and Technology Department of Information Technology Salem India Sri Shanmugha College of Engineering and Technology Department of Biomedical Engineering Salem India

ISBN: (纸本)9798350384369

Bio-electric signal like Electromyography (EMG) can measure signal data from nerves and muscles separately in the particular region of affected nerve or muscles from a Human Being. For incorporating these measurements, can use a non-invasive technique. The Surface electrode can be used for measuring these problems in non-invasive fashion. Here, the idea of Internet of Things (IoT) can bring included advantage to applications with bio-electric signals to communicate to the doctors and patients such as human-PC cooperation by incorporating different advances for example, sensors, remote correspondence and information science. In this research, we worked on a remote bio-electric signals to another remote observing handling framework. A model with the contextual investigation of nerve and muscle signal acknowledgment utilizing 4-channel sEMG signals is executed. A Gaussian filter is prepared from one individual's sEMG signals with 4-nerve regions of human body such as ulnar, radial, median and radial. The introduced IoT application framework is actualized based on an 11-terminal bio-electric signal measuring device, with Arduino based Controller, Gateway, ESP8266 (Wifi) module, Server being the major mediums of remote transmission of signal data. The signal transmits at 35KB/s. In the framework, the ongoing sEMG signal from surface electrode is filtered from noise and other distortions using is given to the controller for performing the operation. © 2024 IEEE.

关键词： Gateways (computer networks)

来源：评论

学校读者我要写书评

暂无评论

Theoretical Framework for Integrating IoT and Explainable AI in a Smart Home Intrusion Detection System 2

Theoretical Framework for Integrating IoT and Explainable AI...

引用

2nd IEEE International Conference on Contemporary Computing and Communications, InC4 2024

作者： Dixit, Mahi Siby, Swetha Maria Jenefa, J. Vetriveeran, Divya Sambandam, Rakoth Kandan Vinodha, D. CHRIST University Department of Computer Science and Engineering Bengaluru India

ISBN: (纸本)9798350383652

Using IoT devices in smart homes brings benefits and security dangers. This study extensively examines various intrusion detection methods within smart home environments. It also suggests a novel hybrid intrusion detection theoretical framework integrating IoT data with Explainable Artificial Intelligence (XAI) approaches. Using information from multiple IoT devices, including motion sensors, door/window sensors, cameras, and temperature sensors, our theoretical framework can create a comprehensive image of the home environment. By effectively detecting new threats, it offers anomaly detection utilizing unsupervised learning approaches to discover potential breaches without tagged data. © 2024 IEEE.

关键词： Smart homes

来源：评论

学校读者我要写书评

暂无评论

QoE-Aware Volumetric Video Caching and Rendering for Mobile Extended Reality Services

引用

IEEE Internet of Things Journal 2025年第12期12卷 21852-21865页

作者： Pei, Yingying Li, Mushu Huang, Xinyu Shen, Xuemin University of Waterloo Department of Electrical and Computer Engineering WaterlooONN2L 3G1 Canada Lehigh University Department of Computer Science and Engineering BethlehemPA18015 United States

In this article, we propose a novel volumetric video caching and rendering approach for an edge-assisted extended reality (XR) system to enhance user Quality of Experience (QoE). Particularly, user QoE consists of visual quality and quality variation. Different quality of volumetric videos are required to be cached, rendered, and delivered to XR devices for different viewing distances within a time latency. Given the limited caching, computing, and communication resources on the edge server, we formulate a long-term user QoE maximization problem to jointly optimize video caching and rendering by considering user locations and viewing distances. To solve this problem, we first design an online optimization algorithm in which caching decisions are obtained using a regularization technique. We then develop a low-complexity binary search algorithm to determine optimal rendering quality. Extensive simulations are conducted to demonstrate that our proposed approach outperforms benchmark schemes by an average 46% improvement in terms of long-term user QoE. © 2014 IEEE.

关键词： Video streaming

来源：评论

学校读者我要写书评

暂无评论

Cardio Care: A Predictive Model for Heart Disease Detection 3

Cardio Care: A Predictive Model for Heart Disease Detection

引用

3rd International Conference on Smart Technologies and Systems for Next Generation Computing, ICSTSN 2024

作者： Rohith, R. Senthilnayaki, B. Joshua Dayalan, M. Anna University College Of Engineering Department of Information Science and Technology India Anna University College Of Engineering Department of Computer Science and Engineering India

ISBN: (数字)9798350391565

ISBN: (纸本)9798350391565

Heart Disease is still an epidemic global health concern, so trustworthy prediction models are vital for risk assessment and early detection. In this research, we propose a comprehensive predictive framework leveraging ensemble learning techniques alongside traditional Machine Learning (ML) models to increase forecasting of cardio disease accuracy. Utilizing a dataset sourced from Cardiovascular-Disease-dataset, demographic, clinical, and lifestyle factors were incorporated as features. The performance of Naive Bayes (NB), AdaBoost, Support Vector Classifier (SVC) and Logistic Regression (LR) both individually and within ensemble frameworks, was evaluated using accuracy of 98% and AUROC (Area-Under the Receiver Operating Characteristic Curve) of 99.845% as a primary metric. Our results demonstrate how effective ensemble learning strategies are in obtaining higher accuracy, precision-recall and along with AUROC curve for heart disease prediction compared to individual classifiers. This study underscores the importance of ensemble methods in improving predictive performance and contributing to enhanced clinical decision-making in cardiovascular health management. © 2024 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Portable Executable Analysis for Malware Detection for Reducing Risk 1st

Portable Executable Analysis for Malware Detection for Reduc...

引用

1st International Conference on Intelligent Systems, Blockchain, and Communication Technologies, ISBCom 2024

作者： Kumar, Avinash Chaudhary, Meena Department of Computer Science Engineering Mangalayatan University UP Aligarh India

ISBN: (纸本)9783031823763

In the current era where data and information is the main fuel for business, education, banking, marketing and digital applications used by people. These applications consist of personal and sensitive data. These digital applications are using various technologies that makes it heterogeneous. This heterogeneity creates vulnerabilities in many cases and thus resulting in various threats like, virus, Trojan, spyware and other malicious programs. Malware is one of the deadliest threats in cyber security and it is very challenging to detect malware when entering a system because of its intelligent coding. The reverse engineering is used for detecting malware in classical way which is a time taking process and involves maximum human interventions. Therefore, there is also need of automated defensive mechanism to detect these malwares in order to reduce the duration of mitigation. The less time for accurate detection would result in stopping malware spreading in other part of the organization once it attacks the organization. Therefore, this paper focuses on the Machine Learning concept as one of the major solution for malware detection. This paper also addresses the classical reverse engineering concept that is used to analysis malware. The paper uses, Random Forest, XGBoosting Decision Tree, Gradient Boosting Classifier and SGD Classifier for analysis. Further the Machine Learning models that gives highest accuracy is XGBoosting that gives accuracy of 94.86% followed by random forest which 94.66%. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Reverse engineering

来源：评论

学校读者我要写书评

暂无评论

Bridging the Gap Between Hyperdimensional Computing and Kernel Methods via the Nyström Method 39

Bridging the Gap Between Hyperdimensional Computing and Kern...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Zhao, Quanling Thomas, Anthony Hitchcock Brin, Ari Yu, Xiaofan Rosing, Tajana Department of Computer Science and Engineering UC San Diego United States

ISBN: (纸本)157735897X

Hyperdimensional computing (HDC) is an approach from the cognitive science literature for solving information processing tasks using data represented as high-dimensional random vectors. The technique has a rigorous mathematical backing, and is easy to implement in energy-efficient and highly parallel hardware like FPGAs and "processing-in-memory" architectures. The effectiveness of HDC in machine learning largely depends on how raw data is mapped to high-dimensional space. In this work, we propose NysHD, a new method for constructing this mapping that is based on the Nyström method from the literature on kernel approximation. Our approach provides a simple recipe to turn any user-defined positive-semidefinite similarity function into an equivalent mapping in HDC. There is a vast literature on the design of such functions for learning problems. Our approach provides a mechanism to import them into the HDC setting, expanding the types of problems that can be tackled using HDC. Empirical evaluation against existing HDC encoding methods shows that NysHD can achieve, on average, 11% and 17% better classification accuracy on graph and string datasets respectively. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Review on Meta-Learning: How Artificial Intelligence and Machine Learning Can Learn to Adapt Quickly 3

A Review on Meta-Learning: How Artificial Intelligence and M...

引用

3rd International Conference on Electronics and Renewable Systems, ICEARS 2025

作者： Khadse, Shrikant Gourshettiwar, Palash Pawar, Adesh Faculty of Engineering and Technology Wardha442001 India Faculty of Engineering and Technology Department of Computer Science and Medical Engineering Wardha442001 India Department of Computer Science and Medical Engineering Maharashtra Wardha442001 India

ISBN: (纸本)9798331509675

Meta-learning aims to create Artificial Intelligence (AI) systems that can adapt to new tasks and improve their performance over time without extensive retraining. The advent of meta-learning paradigms has fundamentally changed how Artificial Intelligence (AI) and Machine Learning (ML) are handled, constantly reshaping these fields. Research study reviews the broad field of meta-learning, highlighting its critical function in bridging the AI-ML divide to improve adaptability. The study starts with a review of past developments, following the development of meta-learning algorithms and their underpinning theories. The historical view lays the groundwork for understanding the course of this dynamic regulation, spanning from early efforts in probabilistic program induction to modern discoveries in model-agnostic meta-learning. The study explores multiple meta-learning applications in AI and ML, revealing how they affect financial forecasting, computer vision, natural language processing, autonomous cars, health informatics, robotics, and personalized recommendation systems. When seen from the perspective of adaptive intelligence, meta-learning may be effectively applied to conditions with limited data, hyperparameter optimization, few-shot learning, and quick adaption in reinforcement learning settings. © 2025 IEEE.

关键词： Contrastive 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：