检索结果-内蒙古大学图书馆

16th IEEE International Conference on Computational Intelligence and Communication Networks, CICN 2024

作者： Kumari, Vishakha Bhadoria, Robin Singh National Institute of Technology Department of Computer Science & Engineering Himachal Pradesh Hamirpur India

ISBN: (纸本)9798331505264

In recent years, many brands have started incorporating anime characters into their marketing strategies to boost brand recognition and appeal to a broader audience. These generated characters can also be utilized in online games, further enhancing creativity within the entertainment industry. However, image generation in style transfer tasks presents significant challenges due to the complex variations seen in anime images. It is crucial to retain key features, such as emotions and gestures, during image generation. Generative models like Denoising Diffusion Probabilistic Models (DDPMs) are effective in producing high-quality and detailed images. They work by progressively refining noisy inputs, making them well-suited for capturing intricate details like emotions and gestures. However, the sampling process in DDPMs requires running a Markov chain through numerous steps, making the process computationally expensive. To address these challenges, Denoising Diffusion Implicit Models (DDIMs) have been introduced. DDIMs generate high-quality samples with improved efficiency by using a more implicit, deterministic method for denoising at each stage, significantly speeding up the image generation process. © 2024 IEEE.

关键词： Markov chains

来源：评论

学校读者我要写书评

暂无评论

JAR-Desktop Assistant 8

JAR-Desktop Assistant

引用

8th IEEE International Conference on Computing, Communication, Control and Automation, ICCUBEA 2024

作者： Hindoriya, Dhairya Mandavgane, Prajwal Bhowmik, Jash Nair, Rohan Tiwari, Devaansh Talele, Partvina Dr Vishwanath Karad Mit Wpu Department of Computer Engineering & Technology Pune India

ISBN: (纸本)9798350391770

In this paper, present JAR, a sophisticated desktop assistant meticulously crafted to redefine task execution by seamlessly blending voice and text inputs. JAR represents a paradigm shift in desktop interaction, empowering users with swift and intuitive control over their computing environment. By deftly managing application launches, file organization, and system adjustments based on user directives, JARVIS eliminates the drudgery of manual navigation, heralding a new era of productivity *** to JAR's prowess are its advanced processing algorithms, meticulously engineered to accurately interpret and execute user commands. This technological prowess enables JAR to engage in natural and intuitive interactions, effortlessly understanding and fulfilling user requests with precision. Moreover, JAR boasts a customizable interface and a suite of accessibility features, ensuring a tailored experience that caters to diverse user preferences and needs. At the heart of JAR lies its commitment to efficiency. Through efficient task management, JAR streamlines workflows, liberating users from mundane tasks and enabling them to focus on more meaningful endeavors. Whether it's organizing files, scheduling tasks, or fine-tuning system settings, JARVIS excels in optimizing user productivity while conserving valuable time and *** rigorous evaluation and user feedback, substantiate JAR's effectiveness in enhancing desktop productivity and facilitating seamless computing experiences. By presenting JAR as a versatile and user-centric solution tailored to modern computing needs, our paper contributes to the advancement of desktop assistant technology, paving the way for a future where human-computer interaction is intuitive, efficient, and empowering. © 2024 IEEE.

关键词： Personal digital assistants

来源：评论

学校读者我要写书评

暂无评论

Machine Learning-Based Trustworthy Diabetes Prediction Model 16

Machine Learning-Based Trustworthy Diabetes Prediction Model

引用

16th International Conference on COMmunication Systems and NETworkS, COMSNETS 2024

作者： Aruna Devi, B. Karthik, N. National Institute of Technology Puducherry Department of Computer Science and Engineering Puducherry Karaikal India

ISBN: (纸本)9798350383119

Diabetes is a condition that develops when the blood sugar is above average level. Diabetes shoots up the risk of eye, kidney, nerve, and heart problems. By adopting suitable measures to prevent or manage blood sugar level may reduce the chances of getting diabetes-related health issues. Medical data collection is not done on a regular basis but is determined by the patient's condition and other clinical or administrative factors. A trustworthy model is free from missing values, faulty data and makes reliable predictions. Factors like data quality, anomalies, and model selection play a significant role in building a trustworthy model. Hence, this work concentrates on the prediction of diabetes by considering the following issues: 1) missing values in the dataset, 2) an imbalanced dataset and the presence of anomalies, and 3) diabetes prediction using Machine learning (ML) algorithm. The main objective of this work is to propose a trustworthy diabetes prediction model for an incomplete and imbalanced dataset using ML-based imputation, techniques for balancing datasets, and anomaly detection. © 2024 IEEE.

关键词： anomalies diabetes imbalanced dataset missing values

来源：评论

学校读者我要写书评

暂无评论

Dipper Throated Optimization for Detecting Black-Hole Attacks inMANETs

引用

computers, Materials & Continua 2023年第1期74卷 1905-1921页

作者： Reem Alkanhel El-Sayed M.El-kenawy Abdelaziz A.Abdelhamid Abdelhameed Ibrahim Mostafa Abotaleb Doaa Sami Khafaga Department of Information Technology College of Computer and Information SciencesPrincess Nourah bint Abdulrahman UniversityP.O.Box 84428Riyadh11671Saudi Arabia Department of Communications and Electronics Delta Higher Institute of Engineering and TechnologyMansoura35111Egypt Faculty of Artificial Intelligence Delta University for Science and TechnologyMansoura35712Egypt Department of Computer Science Faculty of Computer and Information SciencesAin Shams UniversityCairo11566Egypt Department of Computer Science College of Computing and Information TechnologyShaqra University11961Saudi Arabia Computer Engineering and Control Systems Department Faculty of EngineeringMansoura UniversityMansoura35516Egypt Department of System Programming South Ural State UniversityChelyabinsk454080Russia Department of Computer Sciences College of Computer and Information SciencesPrincess Nourah Bint Abdulrahman UniversityP.O.Box 84428Riyadh11671Saudi Arabia

In terms of security and privacy,mobile ad-hoc network(MANET)continues to be in demand for additional debate and *** more MANET applications become data-oriented,implementing a secure and reliable data transfer protocol becomes a major concern in the ***,MANET’s lack of infrastructure,unpredictable topology,and restricted resources,as well as the lack of a previously permitted trust relationship among connected nodes,contribute to the attack detection burden.A novel detection approach is presented in this paper to classify passive and active black-hole *** proposed approach is based on the dipper throated optimization(DTO)algorithm,which presents a plausible path out of multiple paths for statistics transmission to boost MANETs’quality of service.A group of selected packet features will then be weighed by the DTO-based multi-layer perceptron(DTO-MLP),and these features are collected from nodes using the Low Energy Adaptive Clustering Hierarchical(LEACH)clustering *** is a powerful classifier and the DTO weight optimization method has a significant impact on improving the classification process by strengthening the weights of key features while suppressing the weights ofminor *** hybridmethod is primarily designed to combat active black-hole *** the LEACH clustering phase,however,can also detect passive black-hole *** effect of mobility variation on detection error and routing overhead is explored and evaluated using the suggested *** diverse mobility situations,the results demonstrate up to 97%detection accuracy and faster execution ***,the suggested approach uses an adjustable threshold value to make a correct conclusion regarding whether a node is malicious or benign.

关键词： Black-hole attack mobile ad-hoc network optimization dipper throated optimization

来源：评论

学校读者我要写书评

暂无评论

Prediction of Pneumonia from 3D CT Images Employing Deep Neural Network based Feature Extraction Method 26

Prediction of Pneumonia from 3D CT Images Employing Deep Neu...

引用

26th International Conference on computer and Information technology, ICCIT 2023

作者： Sima, Tahera Khatun Islam, Rafiqul Dhaka University of Engineering & Technology Department of Computer Science and Engineering Gazipur Bangladesh

ISBN: (纸本)9798350359015

Pneumonia is an inflammatory lung infection that can cause life-threatening consequences such as difficulty breathing, fever, and chest pain. Early detection enables timely action, which reduces the severity of the ailment and improves patient outcomes. However, because of the complexity and diversity of its indications, pneumonia prediction poses considerable problems, making accurate diagnosis and prognosis difficult. In this work, a novel 3D feature extraction method for pneumonia prediction from computed tomography (CT) image volume is proposed. A 3D convolution neural network with rigorous pre-processing processes is used to construct the feature extraction method. The obtained features are then utilized for making decisions in which a number of layers are put together to develop the pneumonia prediction model. A 3D CT image dataset with 160 volumes and 40 volumes for training and testing respectively were used for the experimental evaluation. Several performance indicators were employed to evaluate performance, and cutting-edge methods were utilized to compare results. From the experiment, the proposed method achieved 95% training and 85% validation accuracy in which the state of art 3D CNN models accuracy reached up to 88-92% and 76-80% respectively. In conclusion, it was shown that the suggested algorithm outperforms others in terms of predicting pneumonia from 3D CT volume. © 2023 IEEE.

关键词： classification Convolution neural network CT imaging Feature extraction Pneumonia

来源：评论

学校读者我要写书评

暂无评论

A Comparative Analysis of Eye Movement and Gaze Tracking Algorithms 2nd

A Comparative Analysis of Eye Movement and Gaze Tracking Alg...

引用

2nd International Conference on Human-Centric Smart Computing, ICHCSC 2023

作者： Advith, N.N. Sangeetha, J. Dhanunjaya Reddy, B. Reddy, Pagidala Saketh Venugopal Achari, S. Department of Computer Science and Engineering M S Ramaiah Institute of Technology Bangalore India

ISBN: (纸本)9789819977109

Eye gaze and movement tracking is an important aspect in various fields. They are seeing increased usage in medicine, psychology, education and other emerging technologies such as virtual reality (VR) and augmented reality (AR). In this paper, eye movement and gaze tracking algorithms are discussed. These include event-driven eye segmentation-based algorithm, eye aspect ratio and gaze ratio-based algorithm, cumulative distribution function, projection function and edge analysis algorithm. Each algorithm has a different use case and can be used based on the necessity of the application. The working of the algorithm is understood with the help of implementations, and the obtained results are analysed. These algorithms have a lot of applications in the real world owing to the improvement in speeds or accuracy compared to other existing algorithms. These involve real-time applications such as support systems for bedridden patients to control the applications in their environment and to communicate effectively. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Eye tracking

来源：评论

学校读者我要写书评

暂无评论

Performance Evaluation of LC Materials for Display and Non-display Applications in Ku-Band 6x6 Antenna Array Structure

Performance Evaluation of LC Materials for Display and Non-d...

引用

2024 IEEE International Workshop on Antenna technology, iWAT 2024

作者： Chang, Yun-Hao Chou, Hsi-Hsir National Taiwan University of Science And Technology Department of Electronic And Computer Engineering Taipei Taiwan

ISBN: (纸本)9798350314755

This research focuses on the evaluation of LC materials for display and non-display applications in a Ku-Band 6x6 antenna array structure. Conventional LC materials for display applications i.e. Merck E7 were used to compare with the LC materials that have been developed for EM wave applications i.e. Merck GT7-29001 and JNC ZOC-A017XX. In the proposed antenna array, a slotted coupling feeding method was employed. Numerical simulations demonstrate that all LC materials can achieve beam scanning ranges of over ±45 degrees, exhibiting excellent gain and directivity. However, JNC ZOC-A017XX LC materials can achieve a better frequency tunability of over 6.4%. © 2024 IEEE.

关键词： Liquid crystals

来源：评论

学校读者我要写书评

暂无评论

Deep Learning and Dynamic BPSO for Road Accident Severity Prediction using Twitter Data 15

Deep Learning and Dynamic BPSO for Road Accident Severity Pr...

引用

15th International Conference on Computing Communication and Networking Technologies, ICCCNT 2024

作者： Raul, Sanjib Kumar Rout, Rashmi Ranjan Somayajulu, Dvln National Institute of Technology Department of Computer Science and Engineering Telangana Warangal506004 India

ISBN: (纸本)9798350370249

The traffic and medical authorities utilize accident severity prediction through social media postings for better administration and robust emergency response. Deep learning-based models can be used for accident severity prediction using social media data. However, most of the deep learning methods can only perform well when trained with an optimal set of hyper-parameters. This necessitates the use of meta-heuristics in conjunction with deep learning. Moreover, the increase in depth of the networks warrants partial training of the network to make the training process efficient. In this work, we propose a novel partial training-based hybrid deep neural network on convolutional neural networks (CNN) and long short-term memory (LSTM), which is partially trained, and the hyperparameters are optimized using a dynamic version of binary particle swarm optimization (DBPSO) known as accident tweet hybrid deep dynamic BPSO (AT-HDBPSO). Experiments show that the proposed AT-HDBPSO turns out to be efficient in training compared to traditional deep learning-based training. Finally, the proposed method outperforms other baseline and state-of-the-art techniques in prediction accuracy. © 2024 IEEE.

关键词： Tweets

来源：评论

学校读者我要写书评

暂无评论

Sentiment Classification of Movie Reviews with Logistic Regression 5

Sentiment Classification of Movie Reviews with Logistic Regr...

引用

5th International Conference on Sustainable Communication Networks and Application, ICSCNA 2024

作者： Swathi, R. Sri, Aiswaryaa Roshini, Padma SRM Institute of Science and Technology Department of Computer Science and Engineering Chennai600089 India

ISBN: (纸本)9798331530013

This research focuses on developing an automated sentiment analysis system for Tamil text. The system utilizes Natural Language Processing (NLP) techniques, specifically the Bag of Words (BoW) model with CountVectorizer, to extract features from the text data. These extracted features are then fed into a Logistic Regression classifier to predict sentiment as positive, negative, or neutral. The system demonstrates an F1-score of 0.82, indicating high accuracy in sentiment classification. This research has significant implications for businesses and organizations, enabling them to effectively analyze customer feedback, monitor brand reputation, and make data-driven decisions based on public opinion. © 2024 IEEE.

关键词： Logistic regression

来源：评论

学校读者我要写书评

暂无评论

Segmentation of Brain Tumor using Modified Linknet Architecture from MRI Images

Segmentation of Brain Tumor using Modified Linknet Architect...

引用

2024 International Conference on Knowledge engineering and Communication Systems, ICKECS 2024

作者： Suraj Venkatesh Babu, G.S. Skanda Kumar, C.S. Kowshik, R.G. Ashok, K.N. S J C Institute of Technology Department of Computer Science and Engineering Chikkaballapur India

ISBN: (纸本)9798350359688

Segmentation of Cancerous cell is the most significant tasks in medical image processing. It is believed that early diagnosis of cancerous cell is essential for enhancing treatment options and raising patient survival rates. The manual segmentation is dependent on radiotherapist involvement and expertise. MRI scans are often speedy and an excellent diagnostics step for medical professionals than CT scans. As a result, in an emergency, doctors advise getting an MRI scan. However, there is a chance for inaccuracy because there is a lot of MRI data. This has made automatic cancerous cell segmentation a feasible process. Currently, ML methods are in use for segmentation. This research proposes segmentation of cancerous cell using modified LinkNet architecture from MRI images. The proposed modified LinkNet architecture incorporates advanced features such as attention mechanisms and residual connections to improve its ability to capture intricate details and subtle variations within brain images. The model is trained with a diverse and extensive dataset comprising various types and sizes of brain tumors, providing robust performance across different clinical scenarios. © 2024 IEEE.

关键词： Diseases

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：