检索结果-内蒙古大学图书馆

3rd International Conference for Advancement in technology, ICONAT 2024

作者： Naik, K. Jairam National Institute of Technology Raipur Dept. of Computer Science & Engineering Raipur India

ISBN: (纸本)9798350354171

Weeds are problems for crop yields because they exert harmful effects on the yields by competing with cultivated crops for necessary resources like nutrients, sunlight, and soil. As a result, continual attempts are being made to create safer and more effective herbicide formulations. For precision weeding and to reduce pesticide pollution, segmenting weeds in photos is extremely important. However, weeds and crops are comparable in the field setting, making it challenging to precisely segregate weed from intricate field photos. A deep learning-based system for segmenting weeds from photos was proposed in this paper. This algorithm can distinguish between weeds and crops and soil in photos. Utilizing a condensed U-net, this semantic segmentation method was created. An image augmentation strategy was suggested because image tagging for the semantic segmentation of weeds is challenging. The classification algorithms used in the modified U-Net are Support Vector Machine (SVM), Random Forrest (RF) and Decision Tree (DT). These were also used for predicting the weed part in a sample image before their segmentation. The threshold accuracy for segmenting the image using to be around 51.85% with a segmentation time of approximately 01.02 ms whereas our modified U-Netis obtained 91.03% accuracy and the segmentation time of 50.35ms. The results showed the modified U-Net successfully differentiated weeds from images with numerous other plants. This study seeks to demonstrate that the weed-associated image segmentation technique is effectively identifying and separating weeds in intricate field conditions. © 2024 IEEE.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Vortex Ring and Dynamic Lift Generated by Downstroke of Elastic Butterfly Wing 1

Vortex Ring and Dynamic Lift Generated by Downstroke of Elas...

引用

1st International Conference on Robotics, engineering, science, and technology, RESTCON 2024

作者： Haishi, Sei Fuchiwaki, Masaki Kyushu Institute of Technology Graduate School of Computer Science and Systems Engineering Iizuka Japan

ISBN: (纸本)9798350348842

The shape of airfoil contributes to the performance of the airfoil itself. Elastic deformation during unsteady motion not only generates vortices with larger vorticity, but also enables the generation of sustained dynamic lift than rigid moving airfoil. Membrane airfoils exhibit the high performance by elastic deformation with unsteady motion. Butterfly wing, which is an example of application of membrane airfoil, have been shown to generate a pair of vortex rings and dynamic lift through flapping motion. However, it has not been clarified sufficiently how the wing shape responds to changes in dynamic lift and vortex rings. In this study, authors also visualized the vortex ring, simultaneously measured the dynamic lift, and measured the wing shape. When the wing pass through the horizontal position (when the flapping angle φ = 0 deg.), the dynamic lift is at its maximum, and the vortex ring becomes more developed. As a result, the wing chord direction gradually curves, and when the flapping angle φ =-30 deg., the entire wing chord becomes camber shape. Since no deformation occurred in the wingspan direction at any flapping angle in this measurement range, it can be said that camber in the wing chord direction is necessary to generate the dynamic lift and vortex ring. © 2024 IEEE.

关键词： Elastic deformation

来源：评论

学校读者我要写书评

暂无评论

Enhancing Diagnostic Accuracy in Lung Disease:A VIT Approach

Enhancing Diagnostic Accuracy in Lung Disease:A VIT Approach

引用

2024 International Conference on Advances in Data engineering and Intelligent Computing Systems, ADICS 2024

作者： Ajitha, E. Abishekkumaran, S. Deva, J.C. St Joseph's Institute Of Technology Department Of Computer Science And Engineering Chennai India

ISBN: (纸本)9798350364828

In the realm of medical diagnostics, where limited data availability poses a challenge, this project addresses the detection of pulmonary diseases, tuberculosis, Corona Virus using chest X-Radiation images from modest datasets containing fewer than a thousand samples. By harnessing the potential of deep Vision Transformer approach is employed for lung disease classification. A distinctive pipeline is established, encompassing image preceding classification. Comparative analysis with existing frameworks showcases the efficacy of this approach. Remarkably, the study reveals that pretrained models and even simpler classifiers like shallow neural networks can rival complex systems. The framework is also validated against publicly available lung datasets, positioning it as a competitive solution. This method achieves accuracy levels akin to state-of-the-art models while embracing the advantage of fewer trainable parameters. Importantly, the MobileViT based model showcases performance parity with superior solutions, effectively reconciling computational efficiency with diagnostic accuracy. This project pioneers an innovative pathway, transcending data constraints to empower accurate and accessible pulmonary disease detection through a resource-efficient framework. © 2024 IEEE.

关键词： COVID-19

来源：评论

学校读者我要写书评

暂无评论

Understanding the role of human-inspired heuristics for retrieval models

引用

Frontiers of computer science 2022年第1期16卷 11-21页

作者： Xiangsheng LI Yiqun LIU Jiaxin MAO Department of Computer Science and Technology Institute for Artificial IntelligenceBeijing National Research Center for Information Science and TechnologyTsinghua UniversityBeijing100084China

Relevance estimation is one of the core concerns of information retrieval(IR)*** existing retrieval models gained much success in both deepening our understanding of information seeking behavior and building effective retrieval systems,we have to admit that the models work in a rather different manner from how humans make relevance ***’information seeking behaviors involve complex cognitive processes,however,the majority of these behavior patterns are not considered in existing retrieval *** bridge the gap between practical user behavior and retrieval model,it is essential to systematically investigate user cognitive behavior during relevance judgement and incorporate these heuristics into retrieval *** this paper,we aim to formally define a set of basic user reading heuristics during relevance judgement and investigate their corresponding modeling strategies in retrieval *** experiments are conducted to evaluate the effectiveness of different reading heuristics for improving ranking *** on a large-scale Web search dataset,we find that most reading heuristics can improve the performance of retrieval model and establish guidelines for improving the design of retrieval models with human-inspired *** study sheds light on building retrieval model from the perspective of cognitive behavior.

关键词： reading heuristics retrieval model cognitive behavior

来源：评论

学校读者我要写书评

暂无评论

Analyzing Students’ Emotion and Activities in the Classroom: A Rural Education Perspective 4th

Analyzing Students’ Emotion and Activities in the Classr...

引用

4th International Conference on Frontiers in Computing and Systems, COMSYS 2023

作者： Konar, Koushik Suman, Shailabh Chaurasia, Diraj Pal, Aniruddha Saha, Sujoy Electronics and Communication Engineering National Institute of Technology Durgapur India Computer Science and Engineering National Institute of Technology Durgapur India Viterbi School of Engineering University of Southern California Los Angeles United States Computer Science and Engineering Bengal College of Engineering and Technology Durgapur India

ISBN: (纸本)9789819726103

Analyzing the concentration levels of students in a classroom and locating their positions pose significant challenges due to varying environmental conditions and diverse features. Facial expressions can reflect an individual’s mood, with different muscle positions beneath the skin indicating various emotions. Head orientation serves as an additional parameter to generalize student concentration levels. Moreover, different body postures can also provide insights into a person’s mood and concentration. This paper presents a lightweight application designed to analyze student concentration levels in a classroom, particularly to support rural education systems. Our work aims to address the challenges of cost-effectiveness and lightweight implementation suitable for running on affordable smartphones commonly used by rural faculty members. We employ the popular Dlib library for face detection, the FaceNet model for feature extraction, and the Siamese network for face recognition. We achieve 95% accuracy in face recognition using publicly available celebrity datasets, and our in-house dataset collected from NIT, Durgapur yields an 88% accuracy. Additionally, we implement MobileNet transfer learning for emotion recognition, focusing on relevant emotions such as Anger, Disgust, Fear, Happy, Neutral, Sad, and Surprise, achieving an accuracy of 73.76%. For Human Activity Recognition, we consider activities such as Clapping, Reading, Raising Hand, Looking Around, and Standing. We employ R-CNN and Random Forest techniques, achieving an accuracy of 64.92% on the in-house NIT, Durgapur dataset. Finally, we develop a mobile app that encompasses all functionalities, including class recording, data synchronization with Internet storage, and registration features for students and volunteers. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

A Smart Survey Analysis using Wireless Sensor Networks in Agriculture 18

A Smart Survey Analysis using Wireless Sensor Networks in Ag...

引用

18th INDIAcom;11th International Conference on Computing for Sustainable Global Development, INDIACom 2024

作者： Shifna, N. Fathima Shrene Thaiyalnayaki, S. Bharath Institute of Higher Education and Research Department of Computer Science and Engineering Chennai India

ISBN: (纸本)9789380544519

Smart agriculture systems are critical for making the best use of highly fertilized croplands as well as limited water and energy resources. Wireless Sensor Networks (WSNs) can be used in various networks without infrastructure to monitor environmental condition. WSN is utilized in agriculture to cut labour costs by providing farmers with a wealth of information on crops, fields, and weather conditions: This paper explores the significant role of WSNs in offering real-time data completion, change agriculture analysis, and control solutions with precautions for farmers. The integration of WSNs in agriculture enables reducing resource wastage, care farming while help crop yield. Wireless sensor networks, comprised of independent sensor nodes with data completion and communication capabilities have the potential to address key challenges in agriculture. These challenges include pest and disease monitoring, efficient resource management, weather forecasting, and environmental sustainability. Key components of smart agriculture using WSNs include environmental monitoring sensors (e.g., temperature, humidity, and soil moisture), independent drones and robots for crop inspection and data analytics platforms. Data aggregation is necessary for the process of collecting detailed, huge sets of data by WSNs, providing observation of crop health, growth patterns, and possible threats. These observations enable predictive maintenance, early pest detection, and flexible crop management strategies. The importance of WSNs in modern agriculture and their effective needs to guide farmers to benefit were summarized in this research work. © 2024 Bharati Vidyapeeth, New Delhi.

关键词： bluetooth general packet radio service long range radio the internet of things wireless sensor network

来源：评论

学校读者我要写书评

暂无评论

Transforming Traditional Medical Appointment Booking with Advanced Technologies and User-Centric Design 3

Transforming Traditional Medical Appointment Booking with Ad...

引用

3rd International Conference on Pervasive Computing and Social Networking, ICPCSN 2023

作者： Mahanthi, Avinash Naidu Jacob, T.Prem Sathyabama Institute of Science and Technology Computer Science and Engineering Chennai India Sathyabama Institute of Science and Technology Chennai India

ISBN: (纸本)9798350322842

Life gets too busy to go to a doctor in character and keep up with the right hospital therapy. The most important motive of this work is to offer patients quite simple and luxurious experience during the appointment with the physician, as well as to addressing the questions that the sufferers provide during the appointment. The Find-My-Doctor acts as a client, and is maintained with the aid of an internet site that acts as a server and at the same time a database containing medical records, doctors, patients, and appointment statistics. The present-day widespread working procedures for registering patients and making appointments are time-eating and extremely cumbersome. Find-My-Doctor is an internet-based application designed to streamline the appointment procedure for more than one scientific/healthcare institution. © 2023 IEEE.

关键词： Appointment Booking System Database Security Full Stack Application MongoDB NodeJS ReactJS

来源：评论

学校读者我要写书评

暂无评论

Decentralized Energy Consumption Analysis Framework for Coordinated EVs Charging 14

Decentralized Energy Consumption Analysis Framework for Coor...

引用

14th International Conference on Cloud Computing, Data science and engineering, Confluence 2024

作者： Kakkar, Riya Agrawal, Smita Tanwar, Sudeep Institute of Technology Nirma University Department of Computer Science and Engineering Gujarat 382481 India

ISBN: (纸本)9798350344837

With the modernization of the transportation system, EVs penetration has been promoted significantly and holds great potential by maintaining energy sustainability for the greener environment. Nevertheless, owing to the vast number of EVs arriving at the CS, there is a high possibility of imbalanced energy exchange between EV and CS, which also disrupts the working of the smart grid. Moreover, security and privacy issues during EV energy transactions are not handled by the researchers to that extent. Thus, we propose a blockchain-based EV energy consumption analysis framework for predicting Evs' SoC in the smart grid environment. We have applied a sequential model to predict EVs SoC based on the various effecting parameters using optimizers such as Adam, Adadelta, and RMSprop. The incorporated IPFS protocol is combined with the blockchain to ensure the reliability and availability of the proposed framework during the EV energy consumption prediction. Finally, the proposed framework is analyzed and evaluated considering various standard performance metrics such as loss using MSE, MAE, and SoC error prediction in which the sequential model with Adam outperforms other optimizers in terms of minimum error and loss. © 2024 IEEE.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

A Multichannel CNN-LSTM Approach for Fake News Detection: A Comparative Study

A Multichannel CNN-LSTM Approach for Fake News Detection: A ...

引用

2024 International Conference on Integration of Emerging Technologies for the Digital World, ICIETDW 2024

作者： Johnson, Deepika Roselind Srivats, R. Kalyanasundaram, V. Saimirra, R. Vellore Institute of Technology School of Computer Science and Engineering Chennai Campus Chennai India

ISBN: (纸本)9798331541170

The proliferation of fake news across various language sources poses a significant challenge in ensuring the dissemination of accurate and reliable information. Addressing this issue is crucial for maintaining the integrity of news content and public trust. We developed a novel approach combining Convolutional Neural Networks (CNN) for deep feature extraction and Long Short-Term Memory (LSTM) networks for subsequent detection of fake news. Our approach utilizes a Multichannel combined CNN-LSTM architecture. We collected an extensive dataset comprising 40,000 unique news articles from diverse sources to evaluate our model. Additionally, we integrated Gaussian and Random Forest models to benchmark performance. Our findings revealed that the LSTM component of the model achieved a remarkable accuracy of 97%, significantly outperforming the CNN's accuracy of 75%. The Gaussian model also recorded an accuracy of 75%, while the Random Forest model matched the LSTM's performance with an accuracy of 97%. The study demonstrates the effectiveness of our hybrid CNN-LSTM approach in detecting fake news, highlighting its potential as a robust tool for combating misinformation. Our results contribute to the growing body of research in fake news detection and underscore the value of leveraging deep learning techniques to enhance the accuracy and reliability of news content. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Cheating Detection in Online Exam: A Comprehensive Survey 1

引用

8th International Conference on Information and Communication technology for Competitive Strategies, ICTCS 2023

作者： Bhowmik, Pratya Das, Smita National Institute of Technology Agartala Department of Computer Science and Engineering Tripura Agartala India

ISBN: (数字)9789819702107

ISBN: (纸本)9789819702091

Due to COVID-19, many educational institutes throughout the world shifted their means of teaching from offline to online. Online examination became more challenging while testing the academic skills or depth of knowledge of a student. The alarming situation ascends when a student practices unfair means during an online exam. In this paper, a survey is carried out based on recent research works where initially the reason behind cheating in exams is analyzed. Subsequently, detection measures for cheating during and after exams have also been discussed. Finally, various prevention measures for cheating have been studied to identify new research challenges in this field. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Students

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：