检索结果-内蒙古大学图书馆

Electronics and Renewable Systems (ICEARS), International Conference on

作者： M Sirish Kumar R Usha B Rama Kantha Reddy S Ramachandra P Jaya Prakash B Swetha Dept. of Data Science School of Computing Mohan Babu University India CSE Madanapalle Institute of Technology and Science Madanapalle CSE (AI and ML) Sri Venkateswara College of Engineering Tirupati CSE Mother Theresa Institute of Engineering and Technology Palamaner Department of IT Sri Venkateswara College of Engineering Tirupati Dept. of Master of Computer Applications Mohan Babu University India

ISBN: (数字)9798331509675

ISBN: (纸本)9798331509682

This study introduces a system designed to identify pests in crops and classify them as either beneficial or harmful. The project begins by providing a comprehensive overview of various pest identification methods, analyzing their strengths and limitations. To address the problem, a categorization approach is proposed that incorporates convolutional neural networks (CNN) to build the pest identification and classification model. The model was trained using a dataset containing images of different pest species. Extensive testing was conducted on a large dataset, and the system's performance was validated against multiple traditional classification models. The proposed framework achieved a classification accuracy of 90%, outperforming conventional methods. This research highlights agriculture's vital role in the economy and underscores the potential of advanced technologies in supporting sustainable farming practices.

关键词： Deep learning Accuracy Insects System performance Transfer learning Crops Pesticides Agriculture Convolutional neural networks Testing

来源：评论

学校读者我要写书评

暂无评论

Advanced Deep Learning Approaches for Content-Based Image Retrieval System in Skin Cancer Diagnostics

Advanced Deep Learning Approaches for Content-Based Image Re...

引用

Intelligent Computing and Sustainable Innovations in Technology (IC-SIT), International Conference on

作者： Issac Neha Margret Sai Bhargav Kasetty Nuthalapati Sudha Rajesh Kumar Ojha K. Sai Madhuri K. Rajakumar SCOPE V.I.T University Vellore Tamilnadu India dept. of CSE - DS AI&DS CYS VNR VJIET Hyderabad Telangana India dept. of Computer Science & Engineering Silicon University Bhubaneswar Odisha India dept. of CSE - Data Science BVRIT Narsapur Hyderabad Telangana India

ISBN: (数字)9798350369175

ISBN: (纸本)9798350369182

The objective of this paper is to develop and assess the performance of a deep learning model-based content skin cancer detection image retrieval system. In this regard, CNN, VGGNet, ResNet, DenseNet, InceptionNet, and MobileNet were tested on recall, accuracy, mean average precision, F1, and precision metrics. VGGNet performed best among them, with an accuracy of 92.3%, outperforming all other models in precision, F1-score, and recall. CNN also gave the best performance with 91.5% accuracy. The CBIR system retrieved relevant images for the given lesions, especially melanoma lesions, which were relevant and high in precision within the top 5 retrieved images. These results also confirm the efficiency of CNN and VGGNet in enhancing accuracy during the retrieval of skin cancer diagnosis images.

关键词： Deep learning Measurement Technological innovation Accuracy computational modeling Image retrieval Neural networks Melanoma Lesions

来源：评论

学校读者我要写书评

暂无评论

Big OLAP data Cube Compression Algorithms in Column-Oriented Cloud/Edge data Infrastructures

Big OLAP Data Cube Compression Algorithms in Column-Oriented...

引用

IEEE International Conference on Multimedia Big data (BigMM)

作者： Alfredo Cuzzocrea The Big Data Engineering and Analytics Laboratory University of Calabria Rende Italy Dept. of Computer Science University of Paris City Paris France

This paper provides a brief overview on the innovative problem of devising and implementing big OLAP data cube compression algorithms in column-oriented Cloud/Edge data infrastructures, an emerging need for next-gener...

关键词：

来源：评论

学校读者我要写书评

暂无评论

Predicting the Risk of Stroke Based on Imbalanced data Set with Missing data 2

Predicting the Risk of Stroke Based on Imbalanced Data Set w...

引用

2nd IEEE International Conference on Electronic Technology, Communication and Information, ICETCI 2022

作者： Xie, Haoyu Fan, Xuwei Zhang, Yidan Zhan, Yihong Xu, Weijian Huang, Lianfen National Institute for Data Science in Health and Medicine Xiamen University Xiamen China Xiamen University Dept. of Information and Communication School of Information Xiamen China First Affiliated Hospital of Xiamen University Dept. of Neurology Xiamen China College of Information Engineering Jimei University Xiamen China

ISBN: (数字)9781728181158

ISBN: (纸本)9781728181158

How to prevent stroke in daily life and grasp the possibility of illness as early as possible have become important problems. In this paper, we predict the possibility of the disease through the physiological indicators of the at-risk population. In this process, we first dealt with the common problems of missing data and imbalance between classes in medical data sets, and then we combined multiple simple neural networks and XGBoost tree model through ensemble learning methods. After training this strong classifier with the processed data set, we used this model to predict the incidence of stroke and compared it with the results of other classifiers. After several experiments, we got an average accuracy rate of 75.77% and an average specificity of 78.8%, which means that our model can better identify high-risk individuals while ensuring a certain overall accuracy rate. On the whole, our work can quickly derive disease risk through easily accessible physiological indicators, and provide references for early diagnosis and treatment of stroke. © 2022 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Enhancing Lighter Neural Network Performance with Layer-wise Knowledge Distillation and Selective Pixel Attention

Enhancing Lighter Neural Network Performance with Layer-wise...

引用

International eConference on Computer and Knowledge engineering (ICCKE)

作者： Siavash Zaravashan Sajjad Torabi Hesam Zaravashan Dept. Computer Engineering Iran University of Science and Technology Tehran Iran Data Scientist Part Research Center of AI Tehran Iran

Deep neural networks have made a revolution in different areas of Artificial Intelligence such as image classifi-cation and object detection. However, most of these models are heavy and time-consuming at the inference stage. If we desire to use real-time applications, it’s necessary to lighten them up. However, this could negatively affect the performance of models. One suggested approach for enhancing the capabilities of smaller models involves a technique called knowledge distillation. In this method, a less advanced model, referred to as the student model, learns from and emulates the more advanced teacher model to enhance its performance. This method has been proven as an effective technique to compress the model and increase its accuracy. Previous methods mostly focus on proposing feature transformation and loss functions between the same level’s features to improve the effectiveness. In this paper, we investigate the effect of connections between different layers of teacher and student networks and reveal their great importance. We have employed three different loss functions—attention-driven distillation, hierarchical context loss, and non-local loss—to enhance the classifier’s overall performance. Extensive experiments on the CIFAR-100 dataset show that the proposed method has a great performance improvement. For the benefit of the research community, we will make the code for this study available on GitHub.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Individualizing Glioma Radiotherapy Planning by Optimization of a data and Physics-Informed Discrete Loss

arXiv

引用

arXiv 2023年

作者： Balcerak, Michal Weidner, Jonas Karnakov, Petr Ezhov, Ivan Litvinov, Sergey Koumoutsakos, Petros Zhang, Ray Zirui Lowengrub, John S. Yakushev, Igor Wiestler, Benedikt Menze, Bjoern Dept. of Quantitative Biomedicine University of Zurich Zurich Switzerland Dept. of Computer Science Technical University of Munich Munich Germany Computational Science and Engineering Laboratory Harvard University CambridgeMA United States Computational Science and Engineering Laboratory ETH Zurich Zurich Switzerland Dept. of Mathematics University of California IrvineCA United States Dept. of Nuclear Medicine Technical University of Munich Munich Germany Dept. of Neuroradiology Klinikum Rechts der Isar Munich Germany TranslaTUM Center for Translational Cancer Research Munich Germany

Brain tumor growth is unique to each glioma patient and extends beyond what is visible in imaging scans, infiltrating surrounding brain tissue. Understanding these hidden patient-specific progressions is essential for effective therapies. Current treatment plans for brain tumors, such as radiotherapy, typically involve delineating a uniform margin around the visible tumor on pre-treatment scans to target this invisible tumor growth. This"one size fits all" approach is derived from population studies and often fails to account for the nuances of individual patient conditions. We present the GliODIL framework, which infers the full spatial distribution of tumor cell concentration from available multi-modal imaging, leveraging a Fisher-Kolmogorov type physics model to describe tumor growth. This is achieved through the newly introduced method of Optimizing the Discrete Loss (ODIL), where both data and physics-based constraints are softly assimilated into the solution. Our test dataset comprises 152 glioblastoma patients with pre-treatment imaging and post-treatment follow-ups for tumor recurrence monitoring. By blending data-driven techniques with physics-based constraints, GliODIL enhances recurrence prediction in radiotherapy planning, challenging traditional uniform margins and strict adherence to the Fisher-Kolmogorov partial differential equation (PDE) model, which is adapted for complex cases. Copyright © 2023, The Authors. All rights reserved.

关键词： Constrained optimization

来源：评论

学校读者我要写书评

暂无评论

Development of an Intelligent System for Predictive Analysis of Student Academic Performance Using Machine Learning Techniques

Development of an Intelligent System for Predictive Analysis...

引用

International Conference on Inventive Computation Technologies (ICICT)

作者： Anand Tripathi KTV Reddy Dept. of Artificial Intelligence and Data Science Datta Meghe Institute Of Higher Education and Research Faculty of Engineering and Technology Datta Meghe Institute of Higher Education and Research (Deemed to be University) Wardha

ISBN: (数字)9798331512248

ISBN: (纸本)9798331512255

This research proposes an intelligent system utilizing machine learning techniques to predict student academic performance. A Random Forest classification model was developed based on a dataset consisting of key attributes such as attendance, previous grades, hours spent weekly on studying, medical emergencies, and assignment scores. The model classifies students into three categories: High-Performing, Average, and At-Risk, achieving an impressive accuracy of 99 %. Attendance and previous grades emerged as the key determinants of academic success. To facilitate real-world application, this project also includes an interactive Streamlit-based web application, enabling educators to make instant data-driven predictions by inputting students' academic details. This tool empowers educators with actionable insights, allowing them to implement timely interventions, optimize resource allocation, and adapt learning experiences for improved student outcomes. The study underscores the rapid advancements achieved through predictive analytics in education. By integrating artificial intelligence into pedagogic practice, institutions can proactively address learning difficulties, enhance student engagement, and foster academic excellence.

关键词： Education data visualization Learning (artificial intelligence) Alarm systems Real-time systems Resource management data mining Predictive analytics Intelligent systems Random forests

来源：评论

学校读者我要写书评

暂无评论

AgTech that doesn’t cost the Earth: Creating sustainable, ethical and effective agricultural technology that enhances its social and ecological contexts

AgTech that doesn’t cost the Earth: Creating sustainable, e...

引用

2022 Conference on Artificial Life, ALIFE 2022

作者： Dorin, Alan Penn, Alexandra S. Siqueiros, Jesús M. Computational and Collective Intelligence Dept. of Data Science & AI Faculty of Info. Tech. Monash University Australia Centre for the Evaluation of Complexity Across the Nexus Centre for Research in Social Simulation Dept. of Sociology University of Surrey United Kingdom Unidad Académica del IIMAS en el Estado de Yucatán IIMAS UNAM Mexico

To feed the growing human population we require increased food production and security, while using less land and causing less environmental damage. Significant changes in agriculture are needed to meet these demands. One widely touted solution is smart, AI-enhanced Agricultural Technology. In this article we argue that improved technology is insufficient to address the needs of many farmers, but that by taking a whole-of-system approach native to Artificial Life we can shift towards creating sustainable, ethical and effective AgTech. This can innovate industrial agriculture in developed nations and benefit small landholders from vulnerable communities, whilst reducing the environmental impacts of food production globally. © Artificial Life Conference Proceedings 2022.

关键词： Sustainable agriculture

来源：评论

学校读者我要写书评

暂无评论

Machine Learning Model for Prediction of Smartphone Addiction

Machine Learning Model for Prediction of Smartphone Addictio...

引用

Expert Clouds and Applications (ICOECA), International Conference on

作者： S Likhith Chengamma Chitteti M Dharani V Nivedhitha N Guna Geethika V Godwin Dept. of Information Technology Mohan Babu University(Erstwhile Sree Vidyanikethan Engineering College) A.Rangampet Tirupati India Dept. of Data Science Mohan Babu University(Erstwhile Sree Vidyanikethan Engineering College) A.Rangampet Tirupati India Dept. of ECE Mohan Babu Universuy(Erstwhile Sree Vidyanikethan Engineering College) A.Rangampet Tirupati India

ISBN: (数字)9798350385793

ISBN: (纸本)9798350385809

Smartphone addiction has become a growing concern in recent years, with increasing numbers of people exhibiting symptoms such as excessive phone use, loss of productivity, and even physical and psychological health problems. As a result, there is a need to develop effective tools for predicting smartphone addiction and identifying those at risk. In this study, we built a ML model used for predicting smartphone addiction using data collected from a survey of smartphone users. Demographics, phone usage habits, and a range of psychological issues like stress, anxiety, and depression were all covered in the poll. A popular and effective machine learning method, to build our model. In this study, the data is preprocessed by encoding categorical variables and normalizing numerical variables to ensure that the model could learn effectively. Further, the model is trained on some percentage of the data and evaluated its accuracy and its performance on the remaining percentage of the data using several metrics such as accuracy. The results showed that the model has achieved a high accuracy in predicting smartphone addiction. The most important features for predicting addiction were mobile phone usage patterns such as the frequency of checking notifications, the number of hours spent on the phone each day, and the types of apps used most frequently. Other important factors included age, gender, and stress levels. The model developed has several potential applications. It could be used by healthcare professionals to identify individuals who are at risk of developing smartphone addiction and provide appropriate interventions. It could also be used by app developers to design apps those are less addictive and promote healthier phone usage habits. In a brief, this study illustrates both the practicality and efficacy of using machine learning models for predicting smartphone addiction. Further research is needed to validate our findings on larger and more diverse datasets and to ex

关键词： Surveys Adaptation models Accuracy Addiction Psychology Machine learning Human factors

来源：评论

学校读者我要写书评

暂无评论

A Novel Machine Learning Approach to Detect Application Layer DDoS Attacks

A Novel Machine Learning Approach to Detect Application Laye...

引用

Emerging Technology (INCET), International Conference for

作者： V. Jyothsna Sarabu Naga Swetha P. Lalan Kumar Vadde Uday Kumar Putta Kalyan K. Srilakshmi Dept. of Data Science MOHAN BABU UNIVERSITY (Erstwhile Sree Vidyanikethan Engineering College (Autonomous)) Tirupati India Dept. of Information Technology Sree Vidyanikethan Engineering College Tirupati India Sri Padmavathi Women s Degree & PG College TTD Tirupati India

ISBN: (数字)9798350361155

ISBN: (纸本)9798350361162

Attackers use application-layer DDoS (App-DDoS) attacks, which aim to bring down the victim's server by sending fake packets in its direction. Because malicious packets mimic the behavior of legitimate users and contain real source IP addresses, neither attackers nor IDS can distinguish packets from legitimate users. Regardless of the kind, the primary objective of DDoS attackers is to make the victim servers react so slowly that they become unusable or shut down entirely. They overburden the victim server's bottleneck resources in order to do this. For application-layer DDoS attacks, CPU cycles, RAM, I/O bandwidth, disk bandwidth or database bandwidth and TCP/IP stacks are the intended bottleneck resources. Through the use of valid requests, the attacker overwhelms the bottleneck resources in App-DDoS attacks. An attacker overwhelms limited resources with real requests in App-DDoS attacks. Any bot that wants to participate in an attack must first establish a TCP connection to the victim's server, which requires a real IP address to perform such an attack. An App DDoS security technique's primary goal is to identify and separate malicious traffic from legal traffic. Because attackers intentionally generate App-DDoS traffic to mimic real traffic, this problem is challenging. However, experienced hackers are always evolving their toolkits and creating increasingly complex App DDoS attacks, making it harder to identify attack activity. On the other hand, the victim server can stop all traffic coming from the attack sources once the attacked traffic is identified. Over the past decade, a number of traditional, heuristic, and more recently, machine learning (ML)-based methods have been developed to identify and differentiate App-DDoS activity from real traffic. Previously used traditional strategies, such are heuristic and classic approaches, use traffic engineer-programmed rules to identify App DDoS activity. Due to the constantly changing and evolving nature of App-DDo

关键词： Training Accuracy Stacking Bandwidth Denial-of-service attack Feature extraction Boosting

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：