检索结果-内蒙古大学图书馆

2023 International Conference on Recent Advances in science and Engineering technology, ICRASET 2023

作者： Philip Paul Arunodhayam, T. Vadde, Akhil Raj Kumar, Thimmampali Prasanna Silas, Salaja Gandu, Shalem Preetham Harshith Kumar, Chamarti Karunya Institute of Technology and Sciences Dept. of Computer Science and Engineering Coimbatore India College of Engineering and Computing George Mason University Data Analytics Engineering VA Fairfax22030 United States

ISBN: (纸本)9798350306927

Underwater Wireless Sensor Networks (UWSNs) are increasingly being used for various applications, such as environmental monitoring, underwater exploration, and oceanographic research. protocols that consume less energy for underwater wireless sensor networks (UWSNs) are still a difficult undertaking because of the harsh conditions present underwater and the restricted battery capacity of the sensor nodes. This research paper proposes an optimized multi-Hop routing protocol using Chimp Optimization and Self-Organizing Map (SOM). The proposed technique is compared with three popular routing protocols - AODV, DSDV, and DSR in terms of network lifetime and packet delivery ratio. Chimp Optimization algorithm as well as SOM are used to improve network performance. The findings indicate that the put-forward technique exceeds the performance of existing routing protocols, as it increases network lifetime, PDR and PLR while decreasing packet loss ratio. The network lifetime of the put-forward technique is 1039.42 seconds, which is higher than AODV, DSDV, and DSR. Similarly, the PDR of the proposed technique is 97.38%, which is comparatively higher than the three routing protocols. Moreover, the PLR of the proposed technique is 2.62%, which is much lower than AODV, DSDV, and DSR. The proposed technique based on Chimp Optimization and SOM can effectively optimize the multi-Hop routing protocol in underwater wireless sensor networks to achieve sustainable energy efficiency, thus providing important insights for researchers and practitioners to enhance the performance of underwater wireless sensor networks. © 2023 IEEE.

关键词： Energy efficiency

来源：评论

学校读者我要写书评

暂无评论

Sentiment Analysis on Twitter data of Omicron (B.l.l.529) using Natural Language Processing

Sentiment Analysis on Twitter Data of Omicron (B.l.l.529) us...

引用

2022 IEEE Conference on Interdisciplinary Approaches in technology and Management for Social Innovation, IATMSI 2022

作者： Datta, Suseta Mitra, Poojarini Kundu, Pritam Ministry of Electronics and Information Technology National Institute of Electronics and Information Technology Kolkata India University of Engineering & Management Dept. of Computer Applications Kolkata India University of Engineering & Management Dept. of Computer Science and Engineering Kolkata India

ISBN: (纸本)9781665477192

The COVID pandemic is causing outrageous interference in everyday life and financial activity. Close to two years after the presence of COVID, WHO allotted the variety B.l.l.529 a variety of concern, named 'Omicron'. Online diversion data assessment is created and transformed into a more renowned subject of investigation. In this paper, a sizably voluminous heap of appraisals and assessments are culminated with online redirection information. The evaluations and appearances of Twitter electronic diversion stage clients are summarised and researched by considering sentiment analysis by utilising various natural language processing techniques based on positive, negative, and neutral tweets. All potential outcomes are considered for investigating the feelings of Twitter clients. For the most part, tweets are assessed clearly, and this assessment ensures the headway of this investigation study. Different kinds of analyzers are utilised and measured. The 'TextBlob Sentiment Analyzer' has given the highest polarity score based on positivity, negativity, and neutrality rates in terms of inspiration, pessimism, and impartiality. A total dataset is fully determined and classified with all the analyzers, and a comparative result is also measured to find the ideal analyzer. It is intended to apply boosting machine learning methods to increase the accuracy of the proposed architecture before further implementation. © 2022 IEEE.

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

Distance Validation and Role of High Fidelity VR Environments on Embodiment and Enjoyment

Distance Validation and Role of High Fidelity VR Environment...

引用

International Conference on Computational Intelligence and Knowledge Economy (ICCIKE)

作者： Vishwas G Kini Siddalingaswamy P C Shonraj Ballae Ganeshrao Dept. of Computer Science & Engg. Manipal Institute of Technology Manipal Academy of Higher Education Manipal India Dept. of Optometry Manipal College of Health Professions Manipal Academy of Higher Education Manipal India uGDX Institute of Technology Hyderabad India

Gamification, especially in Virtual Reality (VR) have been gaining importance lately for which there arises a need in understanding the interaction mechanism as to which would lead to engagement and motivation. To assess this, our work uses a virtual hand representation to embody the user in three different VR environment of varying interaction fidelity. Through both qualitative and quantitative data gathered, we assess the users’ perceived sense of embodiment, engagement, and motivation. Results show that hand tracking interactions increase the sense of body ownership but lacks tracking reliability and haptic feedback. The virtual controller representation showcased better sense of agency and faster learning towards interactions. The sense of embodiment, engagement and motivation was found to be the highest in the high-fidelity VR *** a sub part of this work, we also showcase how distances can be measured in virtual environments especially in the stereoscopic Head Mounted Displays (HMD), VR. The virtual environment measured distances is then compared with the premeasured real-world distance for which the high correlation is observed.

关键词： Correlation Stereo image processing Virtual environments Resists Haptic interfaces Reliability Computational intelligence

来源：评论

学校读者我要写书评

暂无评论

Robust and Reliable Liveness Detection Models for Facial Recognition Systems 20

Robust and Reliable Liveness Detection Models for Facial Rec...

引用

20th International Conference on Frontiers of Information technology, FIT 2023

作者： Anjum, Haris Arshad, Usama Ali, Raja Hashim Ul Abideen, Zain Shah, Muhammad Huzaifa Khan, Talha Ali Ijaz, Ali Zeeshan Siddique, Abu Bakar Imad, Muhammad Gik Institute of Engg. Sciences & Technology Faculty of Computer Science & Engineering Topi Pakistan University of Europe for Applied Sciences Dept. of Technology & Software Engineering Berlin Germany BCMaterials Basque Center for Materials Applications & Nanostructure Spain

ISBN: (纸本)9798350395785

Facial Liveness Detection is instrumental in combating fraudulent practices and identity theft by differentiating genuine faces from forgeries. Given that facial recognition is now an integral part of many sectors like banking and law enforcement, liveness detection has become a vital aspect for maintaining the trustworthiness of these applications. Unfortunately, the utility of prevalent facial liveness detection models is constrained by their lack of generalizability to novel, unseen data, which presents a substantial impediment to practical applications. To mitigate this issue, our research endeavored to construct a reliable and precise facial liveness detection model that can effectively navigate this challenge and ensure consistent performance across diverse datasets. The devised model exhibited excellent accuracy, which attests to its robustness. This research underscores the advantages of employing deep learning methods such as Convolutional Neural Networks (CNNs) as they significantly enhance the model's accuracy. We intend for our findings to drive further research and progress in this critical field, by laying the groundwork for future work that integrates multiple liveness detection methods and collects more varied training data to develop an even more resilient and efficient system. © 2023 IEEE.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Improving distributed denial of service attack detection using supervised machine learning

引用

Measurement: Sensors 2023年 30卷

作者： Fathima, Afrah Devi, G. Shree Faizaanuddin, Mohd Dept.of Computer Applications BSAR Crescent Institute of Science and Technology Chennai India Dept. Of CS & IT Maulana Azad National Urdu University Hyderabad India Dept. of AI & Data Science M.Tech Chaitanya Bharathi Institute of Technology Hyderabad India

Distributed denial-of-service (DDoS) attacks are a big problem for cyber security because they can cause a lot of damage to both people and companies. Distributed Denial of Service (DDoS) attacks have been seen to do a lot of damage to the networks and devices they are aimed at. These hacks slow down networks and use up buffer space, which makes resources unavailable. To solve this problem, "Supervised Machine Learning Models" have been used. Several machine learning techniques, such as Random Forest, K-Nearest Neighbors (KNN), and Logistic Regression, were used to figure out what was normal and what was an attack. This study used a sample of the CSE-CICIDS2018, CSE-CICIDS2017, and CICDoS datasets. The dataset was divided into two parts in which three fourth of the data was used for training and one fourth of the data for testing purpose. The proposed research attempt to classify the DDoS attack by using supervised machine learning classifiers. This approach employs three machine learning classifiers such as Random Forest, KNN and Logistic regression. Then we perform Feature Scaling by using Standard Scaler. Finally, the system was evaluated. Random forest classifier outperformed other classifiers with an accuracy of 97.6 % whereas KNN and Logistic regression achieved 97 % and 91.1 %. The study employed several Supervised Machine Learning techniques, including Random Forest, KNN, and Logistic Regression to identify the most effective algorithm for the test. Results demonstrate that Random Forest outperformed the other models. © The Authors

关键词： Denial-of-service attack

来源：评论

学校读者我要写书评

暂无评论

Deep Learning in Autonomous Robotics 3

Deep Learning in Autonomous Robotics

引用

3rd IEEE International Conference on Interdisciplinary Approaches in technology and Management for Social Innovation, IATMSI 2025

作者： Bisen, Anand Singh Anand, Sami Sujatha, S. Tholkapiyan, M. Kumar, Yogendra Sharma, Madhuri Vikrant University Dept. of Cse & It Gwalior India Lovely Professional University Dept. of Computer Science and Engineering Punjab India K.Ramakrishnan College Dept. of Civil Engineering Trichy India Chennai Institute of Technology Dept. of Civil Engineering Tamil Nadu India Gla University Dept. of Computer Eng. & Applications Mathura India Dept. of Life Sciences CHRI Campus Gwalior India

ISBN: (纸本)9798331521691

Deep learning has become a cornerstone in the development of autonomous robotics, enabling machines to detect, understand, and interact with their environment with precision and efficiency. By leveraging advanced deep neural networks, autonomous robots can process and interpret a wide range of sensory data, including visual, auditory, and tactile inputs. This ability is crucial for tasks like object recognition, scene understanding, and decision-making in complex, dynamic environments. Deep learning algorithms, such as convolutional neural networks (CNNs) and recurrent neural networks (RNNs), provide visual perception, allowing robots to navigate and operate in sophisticated settings. Additionally, reinforcement learning techniques teach robots to make real-time decisions and adjust their actions accordingly. These technological advancements have led to significant progress in applications such as autonomous vehicles, surgical robots, industrial automation, and unmanned aerial vehicles (UAVs). This abstract highlight the various applications and benefits of deep learning in autonomous robotics, emphasizing its role in enhancing the performance and adaptability of robotic systems across diverse fields. © 2025 IEEE.

关键词： Autonomous Robotics Convolutional Neural Network Deep Learning Deep Neural Network

来源：评论

学校读者我要写书评

暂无评论

Exploring the predictive potential of artificial neural networks in enhancing mechanical properties of derivatives of graphene nanocomposites: a data-driven approach

引用

International Journal of Information technology (Singapore) 2025年第2期17卷 999-1005页

作者： Rao, D. Nageswara Dahiya, Mamta Arora, Amit Kumar Jandwani, Paras Verma, Gunjan CSE ACED Alliance University Chikkahagade cross Anekal Bangalore India MAIT Maharaja Agrasen University Himachal Pradesh Solan India Computer Science and Engineering IIT Madras Chennai India Accenture LLP Philadelphia PA United States Dept. of Master of Computer Applications G L Bajaj Institute of Technology and Management Uttar Pradesh Greater Noida India

The given manuscript delves into the realm of materials science and engineering, specifically focusing on the utilization of different derivatives of graphene reinforced in matrix material (DGMM’s) to enhance mechanical properties. Graphene (Gr), with its remarkable characteristics, holds immense promise as reinforcement in composites and nanocomposites (NCs). Using linear regression and artificial neural networks (ANN) framework, this study predicts the weight% of enhanced mechanical properties in DGMMs. By analyzing a dataset comprising various graphene derivatives, matrix materials, processing methods, and resulting enhancements, the ANN model offers valuable insights into the intricate relationships within these NCs. The findings reveal the potential of ANN models in optimizing the design and fabrication processes of DGMMs, thereby accelerating materials development and enabling tailored formulations for specific applications. Also, the given manuscript motivates for future research to enhance the predictive accuracy and broaden the scope of applications for *** confirm the corresponding author is correctly identified and amend if ***, it is *** confirm the inserted city name is correct in Affiliation (3, 4) and amend if ***, it is correct and confirmed © Bharati Vidyapeeth's institute of computer applications and Management 2024.

关键词： Artificial neural networks Graphene Linear regression Nanocomposites Nanomaterial

来源：评论

学校读者我要写书评

暂无评论

Facial Emotion Analysis using Deep Learning for Seamless Human-computer Interaction 2

Facial Emotion Analysis using Deep Learning for Seamless Hum...

引用

2nd IEEE International Conference on Networks, Multimedia and Information technology, NMITCON 2024

作者： Sangeetha, S. Saini, Poonam Banupriya, R. Srimathi, S. Kiruthiga, S. Aarthi, R. Srm Arts and Science College Department of computer Applications and Technology Kattankulathur Changelpattu603203 India Sir Padampat Singhania University Dept. of Computer Science & Engineering Vil. Bhatewar Teh. Vallabhnagar Rajasthan Udaipur India Pgp College Of Engineering and Technology Dept. of Electrical and Electronics Engineering India Saveetha School of Engineering Simats Department of Bio Technology Tamilnadu Chennai India Vel Tech Rangarajan Dr Sagunthala R & D Institute of Science & Technology School of Computing Department of Computer Science & Engineering Chennai India R.M.D Engineering College Department of Ece India

ISBN: (纸本)9798350372892

HCII, or human-computer intelligent interaction, is a new academic subject that tries to make computer use more intuitive. Some say machines need human-level social abilities before interacting with people. These skills include reading emotions. Due to its exponential expansion, facial emotion recognition is becoming essential to face recognition. According on photographs, machine learning can recognise expressions. This paper discusses expression recognition model training datasets. Deep learning for Facial Emotion Recognition (FER) is used in this research to teach robots to recognise and adapt to human emotions. An extensive review of deep learning models, including CNNs and CNNR, emphasises their ability to extract spatial and temporal data needed for emotion classification. FER pipeline components like data collection, preprocessing, and model architecture are examined in the paper. Transfer learning, pre-trained models, and data augmentation are studied to address low-labeled dataset concerns. Detailed model training, validation, and evaluation metrics emphasise performance assessment. This study uses the enlarged CohnKanade (CK+) dataset from a face emotion recognition experiment. The system averaged 92.81% accuracy. Eight emotions were successfully detected by the algorithm. The proposed method for emotion recognition has proven useful. © 2024 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

PoI: Proof of Identity and PoDI: Proof of data Integrity for Secure data Deduplication in the Cloud 2

PoI: Proof of Identity and PoDI: Proof of Data Integrity for...

引用

2nd International Conference on Advances in Computing, Communication, Embedded and Secure Systems, ACCESS 2021

作者： Ebinazer, Silambarasan Elkana Savarimuthu, Nickolas Bhanu, Mary Saira S. Dept. of Computer Applications National Institute of Technology Tiruchirappalli India Dept. of Computer Science and Engg. National Institute of Technology Tiruchirappalli India

ISBN: (纸本)9781728171364

Cloud storage is the decisive service for the organization, hospitals etc., for storing huge amount of data within their budget. But, Cloud Service Providers (CSPs) are facing the major problem of duplicate and redundant data being accumulated by data Owners (DO) in the cloud storages. Deduplication is one of the major technique to solve the above problem but faces the major drawback in the form of security flaws. Secure deduplication is a very promising solution proposed by the researchers for addressing this issue. In this paper, problems like revocation of DOs, brute force attack and duplicate faking attack are addressed as part of secure deduplication. The proposed approach is having two protocols, namely, Proof of Identity (PoI) and Proof of data Integrity (PoDI) which solves the above-mentioned problems. The proposed approach improves the efficiency of secure deduplication, enhances data privacy and addresses data Owner (DO) revocation problem. © 2021 IEEE

关键词： Cloud storage

来源：评论

学校读者我要写书评

暂无评论

Boosting-Based Machine Learning Approaches for Diabetes Prediction using Indian Demographic and Health Survey data

Boosting-Based Machine Learning Approaches for Diabetes Pred...

引用

North Karnataka Subsection Flagship International Conference (NKCon), IEEE

作者： Shanta Kallur Suman Yaligar Puneeth N. Thotad Dept. of Computer Science & Engineering KLE Institute of Technology Affiliated to Visvesvaraya Technological University Hubballi India Dept. of Master of Computer Applications KLE Institute of Technology Affiliated to Visvesvaraya Technological University Hubballi India

ISBN: (数字)9798350364569

ISBN: (纸本)9798350364576

Traditional diagnostic techniques are time-consuming and prone to error. Performance is added however time and cost are reduced by using computer-aided diagnostic methods. This study aims to calculate how healthy boosting-based machine learning classifiers perform in automatically identifying diabetes in the Indian context. For this experiment, Indian demographic and health survey 2021 data on women aged 19 to 79 are considered. This data includes clinical, anthropometric, and biochemical components. 12,103 of the 706,504 responders who tested positive for diabetic testing were considered. The predictive exploration-based boosting machine learning models are adopted, such as adaptive boosting, categorical boosting, extreme gradient boosting, gradient boosting, and light gradient boosting models. Kernel Principal Component Analysis is employed for feature extraction. The Extreme Gradient Boosting model demonstrated strong performance on the diabetes dataset both before and after applying Kernel PCA. The metrics including accuracy, F1-score, precision, and recall for the XGBoost model showed improvements: accuracy increased from 81% to 83%, F1-score from 81% to 82%, precision from 81% to 88%, and recall from 81% to 76%.In contrast, Adaptive Boosting performed poorly, while Categorical Boosting, Gradient Boosting, and Light Gradient Boosting models achieved moderate performance levels. Overall, the model attained optimal performance across metrics such as accuracy, precision, Area Under the Curve (AUC), and recall.

关键词： Surveys Measurement Adaptation models Analytical models Accuracy Predictive models Boosting Diabetes Kernel Principal component analysis

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：