检索结果-内蒙古大学图书馆

2024 International Conference on Advances in Modern Age Technologies for Health and engineering.science, AMATHE 2024

作者： ArunKarthi, T. Shanthi, S. Nirmaladevi, K. Ashwinth, K. Dev, R.B. Rajkumar, N. Computer Science And Engineering Kongu Engineering College Erode India Psna College Of Engineering And Technology Department Of Computer Applications Tamilnadu Dindigul India

ISBN: (纸本)9798350371567

In a world where microblogging has become an integral part of modern life., the sudden outbreak of COVID-19 swiftly infiltrated public opinion on various social networking platforms. With individuals adhering to social distancing measures and self-isolation protocols to combat the coronavirus, expressing their fears and concerns on social media became their primary outlet. In order to obtain a thorough comprehension of the pandemic's effects on individuals' lives and the environments in which they live, we must recognize the critical function of social media as a repository of emotions. This paper delves into the realm of sentiment analysis, focusing on the opinions disseminated through Twitter. Our primary dataset comprises these tweets, which we meticulously processed and converted into tokens for analysis. We performed fine-tuning and added an additional classifier layer to BERT, a pre-trained model, in order to classify these feelings into three categories: positive, negative, and neutral. Subsequently, we scrutinized BERT's performance in carrying out this task. Impressively, the BERT model demonstrated an outstanding accuracy rate of 94 percent on our dataset, supplemented by commendable scores in various evaluation metrics. © 2024 IEEE.

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

Identification of Age, Plumage, and Sex of Bird Species Using Pre-Trained Deep Convolutional Neural Network 2

Identification of Age, Plumage, and Sex of Bird Species Usin...

引用

2nd IEEE International Conference on Intelligent and Innovative Technologies in Computing, Electrical and Electronics, ICIITCEE 2024

作者： Banerjee, Sourik Gupta, Richa Pandian, J. Arun Saranya, S. Mariappan, L. Thanga Vellore Institute of Technology Department of Computer Application Vellore India Vellore Institute of Technology School of Computer Science Engineering and Information Systems Vellore India K.Ramakrishnan College of Engineering Department of Computer Science and Engineering Tiruchirappalli India

ISBN: (纸本)9798350306415

The research aims to identify the age, plumage, and sex of bird species using standard Pre-trained Deep Convolutional Neural Networks (Pre-DCNNs). The proposed work involves collecting various bird images, which are then used for training and validating the pre-trained DCNNs. The dataset contains 200 images of four bird species. The dataset was split into twelve labeled classes of images based on age, plumage, and sex. The standard image manipulation techniques such as cropping, flipping, mirroring, rotating, shearing, and skewing were used as image augmentation techniques to increase the size of the proposed dataset. The proposed data is preprocessed, including feature extraction and data cleaning, to ensure the performance of the Pre-Trained DCNNs. The Pre-Trained DCNNs were trained on 90% of the dataset to recognize patterns in bird images. The accuracy of the pre-trained DCNNs was evaluated using metrics such as classification accuracy. The research acknowledged the advantages and limitations of the standard Pre-Trained DCNNs on the age, plumage, and sex of birds using the images. Also, it compares the performance of the Pre-Trained DCNNs on the proposed bird species image dataset. © 2024 IEEE.

关键词： Bird Plumage Identification Bird Species Identification Deep Convolutional Neural Networks Image Augmentation Pre-trained networks

来源：评论

学校读者我要写书评

暂无评论

Diagnosis of compressive strength of cement based material using deep learning technique

引用

Materials Today: Proceedings 2022年 69卷 1402-1407页

作者： Rajendran, Sasikumar Matheshwaran, P. Deepa, K. Department of Computer Science and Engineering K.Ramakrishnan College of Engineering Trichy India Department of Computer Science and Engineering K.Ramakrishnan College of Technology Trichy India Department of Computer Science and Engineering M. Kumarasamy College of Engineering Karur India

Although the widespread usage of mortars in construction over the last few decades, there is no published method for estimating their strength based on the mix parameters of the mortars themselves. This is owing to the fact that the mortar's compressive forte is very nonlinear in response to the mixture's components. Researchers in this research examined how artificial intelligence might be used to forecast compressive strength for cement-based mortars. In previous studies, artificial networks have been used to map the mechanical possessions of cement-based materials. Overfitting and the difficulty to explain decisions are some of the key drawbacks of this machine learning technique, which have been documented in the literature. This study therefore analyses if deep learning may be used to make predictions. Proposed methodology may accurately estimate mortar's strength when compared to experimental results, according to the results obtained from this study. As expected, machine learning predicted mortar compressive strength more accurately than provided model, however it was discovered during verification. To solve the problem of mortar compressive strength, the built deep learning model has been presented as the best predicting procedure. © 2022

关键词： Mortar

来源：评论

学校读者我要写书评

暂无评论

PANLS: Performance Analysis of Node Localization Scheme in WSNs 3

PANLS: Performance Analysis of Node Localization Scheme in W...

引用

3rd International Conference on Technological Advancements in Computational sciences, ICTACS 2023

作者： Mohan, Yogendra Yadav, Rajesh Kumar Manjul, Manisha Delhi Technological University Department of Computer Science and Engineering Delhi India Department of Computer Science and Engineering New Delhi India

ISBN: (纸本)9798350342338

Node localization (NL) in wireless sensor networks (WSN) has numerous applications, such as maritime rescue, agriculture, and hazardous environments, that heavily rely on the node position. In WSN, node localization is crucial since GPS-enabled sensors are not economical or energy-efficient. Therefore, GPS-enabled sensors are not appropriate for many WSN applications. The exact positioning of sensor nodes has a considerable impact on WSN performance. NL is the process of locating a target node (an unknown node). Gaussian noise and RSSI are practical methods for locating a target node's position. The seagull optimization algorithm and its improved versions are used in this research to improve the localization accuracy of nodes. To enhance the accuracy of NL and improve the randomness of the seagull optimization algorithm a chaotic map is employed in this work to enhance the seagull optimization algorithm (SOA). The performance evaluation of C-SOA is far better than the SOA. © 2023 IEEE.

关键词： chaotic-map Meta-heuristic Optimization Node Localization Wireless Sensor Networks

来源：评论

学校读者我要写书评

暂无评论

Social Distance and Face Mask Detection using vision-based sensors and IP cameras 3

Social Distance and Face Mask Detection using vision-based s...

引用

3rd International Conference on Advances in Electrical, Computing, Communication and Sustainable Technologies, ICAECT 2023

作者： Vineela, A. Devi, G. Lavanya Deekshit, G. Vinay GMR Institute of Technology Department of Computer Science and Engineering Rajam India Department of Computer Science and System Engineering Vishakhapatnam India

ISBN: (纸本)9781665494007

Healthcare systems all over the world are strained as the COVID-19 pandemic's spread becomes more widespread. The only realistic strategy to avoid asymptomatic transmission is to monitor social distance, as there are no viable medical therapies or vaccinations for it. A unique computer vision-based framework that uses deep learning is to analyze the images that are needed to measure social distance. This technique uses the key point regressor to identify the important feature points utilizing the Visual Geometry Group (VGG19) which is a standard Convolutional Neural Network (CNN) architecture having multiple layers, MobileNetV2 which is a computer vision network that advances the-state-of-art for mobile visual identification, including semantic segmentation, classification and object identification. VGG19 and MobileNetV2 were trained on the Kaggle dataset. The border boxes for the item may be seen as well as the crowd is sizeable, and red identified faces are then analyzed by MobileNetV2 to detect whether the person is wearing a mask or not. The distance between the observed people has been calculated using the Euclidian distance. Pretrained models like (You only look once) YOLOV3 which is a real-time object detection system, RCNN, and Resnet50 are used in our embedded vision system environment to identify social distance on images. The framework YOLOV3 performs an overall accuracy of 95% using transfer learning technique runs in 22ms which is four times fast than other predefined models. In the proposed model we achieved an accuracy of 96.67% using VGG19 and 98.38% using MobileNetV2, this beats all other models in its ability to estimate social distance and face mask. © 2023 IEEE.

关键词： computer vision

来源：评论

学校读者我要写书评

暂无评论

Glaucoma Diagnosis From Smartphone Captured Fundus Images Using Deep Learning 11

Glaucoma Diagnosis From Smartphone Captured Fundus Images Us...

引用

11th IEEE International Conference on Advances in Computing and Communications, ICACC 2024

作者： Madhu, K. John, Shinu Mathew Joseph, Asha Abraham, Bejoy APJ Abdul Kalam Technological University Computer Science and Engineering Thiruvananthapuram India St.Thomas College of Engineering and Technology Mattannur Department of Computer Science and Engineering Mattannur India Amal Jyothi College of Engineering Department of Information Technology Kottayam India College of Engineering Muttathara Department of Computer Science and Engineering Thiruvananthapuram India

ISBN: (纸本)9798350379136

The retina contains millions of photoreceptive cells called cones, rods, and blood vessels that nourish these cells. The optic nerve carries visual information from the retina to the brain. Glaucoma is a condition, where optic nerves get damaged often caused by high pressure within the eye. Fundus images provide rich information about the appearance of a patient's retina and optic nerve head region. Even though there are various painless diagnosis methods, conventional fundus photography using Retcams is the most commonly used one. Examinations of the fundus images for structural abnormalities in the optic nerve head region such as increased cup-to-disc ratio, NRR thinning, and Violation of the ISNT rule provide sufficient evidence for the presence of glaucoma. However, conventional fundus imaging costs a lot concerning equipment and operation costs. Nowadays, smartphones can capture retina images and are a cheaper alternative to conventional fundus imaging using retcam devices. So our approach is to analyze smartphone-captured fundus images (SCFI) to detect the presence of glaucoma and provide accurate results at a lower cost. We designed an automated one-step approach-based glaucoma detection system that can detect the presence of glaucoma from smartphone-based fundus images with an accuracy of 93 percent. using a deep learning-based approach, The publicly available smartphone-captured fundus image dataset, BrG is used for conducting ablation studies. © 2024 IEEE.

关键词： Smartphones

来源：评论

学校读者我要写书评

暂无评论

p-Mean Regret for Stochastic Bandits 39

p-Mean Regret for Stochastic Bandits

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Krishna, Anand John, Philips George Barik, Adarsh Tan, Vincent Y.F. Department of Electrical and Computer Engineering NUS Singapore CNRS-CREATE Department of Computer Science NUS Singapore Institute of Data Science NUS Singapore Department of Mathematics NUS Singapore

ISBN: (纸本)157735897X

In this work, we extend the concept of the p-mean welfare objective from social choice theory to study p-mean regret in stochastic multi-armed bandit problems. The p-mean regret, defined as the difference between the optimal mean among the arms and the p-mean of the expected rewards, offers a flexible framework for evaluating bandit algorithms, enabling algorithm designers to balance fairness and efficiency by adjusting the parameter p. Our framework encompasses both average cumulative regret and Nash regret as special cases. We introduce a simple, unified UCB-based algorithm (EXPLORE-THEN-UCB) that achieves novel p-mean regret bounds. Our algorithm consists of two phases: a carefully calibrated uniform exploration phase to initialize sample means, followed by the UCB1 algorithm of Auer et al. Under mild assumptions, we prove that our algorithm achieves a p-mean regret bound of O∼(rT2k|1p|) for all p ≤ −1, where k represents the number of arms and T the time horizon. When −1 ∼(k43 T−41). For the range 0 ∼(qTk), which matches the previously established lower bound up to logarithmic factors. This result stems from the fact that the p-mean regret of any algorithm is at least its average cumulative regret for p ≤ 1. In the case of Nash regret (the limit as p approaches zero), our unified approach differs from prior work of Barman et al., which requires a new Nash Confidence Bound algorithm. Notably, we achieve the same regret bound up to constant factors using our more general method. Copyright © 2025, Association for the Advancement of Artificial Intelligence.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Design & Implementation of API Based Software Defined Networking Architecture 26

Design & Implementation of API Based Software Defined Networ...

引用

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

作者： Nayeem, Tanvir Ahamed Uddin, Md. Riaz Rahman, Md. Habibur Islam, Md. Samiul Dhaka International University Department of Computer Science & Engineering Dhaka Bangladesh University of Dhaka Department of Computer Science & Engineering Dhaka Bangladesh State University of Bangladesh Department of Computer Science & Engineering Dhaka Bangladesh

ISBN: (纸本)9798350359015

Software Defined Networking known as SDN appeared to provide automation across any network system. The SDN architecture is designed to build a flexible and manageable network comparing to traditional networking system. Besides, the SDN plays a vital role in network virtualization, cloud computing, mobility, and programmability to make an efficient network system whereas the traditional networking system has some limitations. In this paper, an SDN architecture has been proposed with API integration using python library on Linux based OpenDaylight framework. The comparative results show that the performance of the proposed SDN architecture is much better than traditional network architecture considering data flow, automated IP address generation, packet transmission consistency. © 2023 IEEE.

关键词： API Data flow IoT IP address Linux OpenDaylight Python Software Defined Networking

来源：评论

学校读者我要写书评

暂无评论

Highly Differentiated Target Detection under Extremely Low-Light Conditions Based on Improved YOLOX Model

引用

computer Modeling in engineering.& sciences 2024年第8期140卷 1507-1537页

作者： Haijian Shao Suqin Lei Chenxu Yan Xing Deng Yunsong Qi School of Computer Jiangsu University of Science and TechnologyZhenjiang212003China Department of Electrical and Computer Engineering University of NevadaLas VegasNV89154USA Zhejiang Geely Automobile Research Institute Ningbo315336China

This paper expounds upon a novel target detection methodology distinguished by its elevated discriminatory efficacy,specifically tailored for environments characterized by markedly low luminance *** methodologies struggle with the challenges posed by luminosity fluctuations,especially in settings characterized by diminished radiance,further exacerbated by the utilization of suboptimal imaging *** envisioned approach mandates a departure from the conventional YOLOX model,which exhibits inadequacies in mitigating these *** enhance the efficacy of this approach in low-light conditions,the dehazing algorithm undergoes refinement,effecting a discerning regulation of the transmission rate at the pixel level,reducing it to values below 0.5,thereby resulting in an augmentation of image ***,the coiflet wavelet transform is employed to discern and isolate high-discriminatory attributes by dismantling low-frequency image attributes and extracting high-frequency attributes across divergent *** utilization of CycleGAN serves to elevate the features of low-light imagery across an array of stylistic *** computational methodologies are then employed to amalgamate and conflate intricate attributes originating from images characterized by distinct stylistic orientations,thereby augmenting the model’s erudition *** validation conducted on the PASCAL VOC and MS COCO 2017 datasets substantiates pronounced *** refined low-light enhancement algorithm yields a discernible 5.9%augmentation in the target detection evaluation index when compared to the original *** Average Precision(mAP)undergoes enhancements of 9.45%and 0.052%in low-light visual renditions relative to conventional YOLOX *** envisaged approach presents a myriad of advantages over prevailing benchmark methodologies in the realm of target detection within environments marked by an acute scarcity of lumi

关键词： Target detection extremely low-light wavelet transformation highly differentiated features YOLOX

来源：评论

学校读者我要写书评

暂无评论

Optimized Extreme Learning Machine Framework for Efficient Ransomware Detection Using Seagull Optimization-Based Feature Selection 2

Optimized Extreme Learning Machine Framework for Efficient R...

引用

2nd IEEE International Conference on Emerging Research in Computational science, ICERCS 2024

作者： Rajululi, G. Govinda Geetha, R. Bebitha, J. Basha, SK Mahaboob Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Department of Computer Science & Engineering Chennai India R.M.K. Engineering College Department of Computer Science & Engineering Chennai India Vel Tech Multi Tech Dr Rangarajan Dr Sakunthala Engineering College Department of Computer Science & Engineering Chennai India TKR College of Engineering and Technology Department of Computer Science & Engineering Telangana India

ISBN: (纸本)9798331534950

Ransomware is becoming a more serious threat to cybersecurity, and conventional detection techniques frequently fail to maintain up with its changing strategies. To overcome this difficulty, this research proposes an extreme learning machine (ELM) framework enhances the system the efficiency in threat identification. The Static and dynamic feature of files is identified using ELM for analyzing their behavior patterns. The Seagull Optimization Algorithm (SGO) is employed for feature selection refining the dataset by eliminating redundant characteristics, to improve detection process. The system model trained with a Support Vector Machine (SVM) to determine which files are malicious and which are safe. The ELM-SGO-SVM framework is evaluated using performance metrics for identify ransomware threats and it has efficacy in early ransomware detection and mitigation by showing that it greatly outperforms existing techniques. However, this proposed method strengthens the cybersecurity defenses against ransomware threat and ensures better protection for important digital threats. © 2024 IEEE.

关键词： Adversarial machine 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：