检索结果-内蒙古大学图书馆

14th International Conference on Computing Communication and Networking Technologies, ICCCNT 2023

作者： Nikhil, Shreyas Sah, Rahul Kumar Kumar Parki, Santosh Tamang, Til Bikram Somashekhara Reddy, D. Mahesh, T.R. Faculty of Engineering and Technology Dept. of Computer Science and Engineering Bangalore India

ISBN: (纸本)9798350335095

Stock price prediction has always been a tough task for all the stakeholders involved. This paper focusses on four different models, namely LSTM, CNN, LSTM-CNN, and Genetic Algorithm-Assisted LSTM-CNN (GA-LSTM-CNN) for stock price prediction. The day-to-day stock prices of a certain company for a period of more than 10 years make up the dataset utilized in this study. Root mean square error (RMSE) has been utilized as performance metric for each model. Outcomes of our experiment show that the GA-LSTM-CNN model performed better than other models with an RMSE value of 0.0064 upon training and an RMSE value of 0.03 upon testing. The GA-LSTM-CNN model combines the strengths of LSTM as well as CNN models with the help of a genetic algorithm, which helps in optimizing the hyperparameters. According to the results, the GA-LSTM-CNN model can be very helpful for the stakeholders in predicting future stock values. © 2023 IEEE.

关键词： Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

Water Region Extraction in Aerial Images Using Deep Learning

Water Region Extraction in Aerial Images Using Deep Learning

引用

2024 International Conference on Intelligent Computing and Sustainable Innovations in technology, IC-SIT 2024

作者： Pandey, Nikita Kumar, Saumya Yadav, Satish Kumar Srivastava, Shashwat Singh, Shomil Gupta, Deepak Pranveer Singh Institute of Technology Dept. of Computer Science and Engineering Kanpur India

ISBN: (纸本)9798350369175

Water bodies are essential component of Earth's surface and accurate water region mapping is crucial for disaster management and environmental monitoring. Existing methods to map water bodies relies on traditional modelling methods that need extensive manual calibration struggle with scalability and lack advanced pattern recognition. This paper evaluates the effectiveness of deep learning-based semantic segmentation models, DeepLabV3+ and U-Net, using aerial images resized to $\mathbf{2 5 6 x} 256$ pixels in mapping water regions in aerial images. DeepLabV3+, with a ResNet50 backbone, and U-Net are trained on a comprehensive flood-affected dataset with preprocessing techniques such as resizing and augmentation. Model performance is assessed using metrics like IoU, F1 score, accuracy, precision, and recall. The results indicate that DeepLabV3+ outperforms U-Net, showing promise for automating water region mapping and improving flood surveys and urban planning. © 2024 IEEE.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Early Detection of ADHD in Children Using Two Learning Approaches

Early Detection of ADHD in Children Using Two Learning Appro...

引用

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

作者： Sherine, M. Selvi Rajendran, P. Hindustan Institute Of Technology And Science Dept Of Computer Science And Engineering Chennai603103 India

ISBN: (纸本)9798350364828

Children with Attention Deficit /Hyperactivity Disorder (ADHD) struggle to focus for longer than a few minutes at a time. The onset of symptoms can occur as early as age 3 or 12, and they may worsen until maturity. For symptoms to be minimised and behavioural techniques to be improved, early diagnosis is critical. Even though it was first identified in the 1940s, after the 1990s, awareness grew. ADHD detection may also be impacted by genetic issues. Boys are treated more often than girls, which makes them less attentive and makes it harder for them to develop objectives. Brain analyses and behavior-related questionnaires are two early diagnostic techniques. The proposed system composed of two phases of diagnosing the ADHD in children. The first phase uses the dataset obtained from screening test in which Random Forest gave the highest accuracy. The second phase uses the Deep Neural Network with attention (DNN-AM) model for the early identification of ADHD in children. It analyses images as a whole, tracking how children with ADHD interact with their surroundings. It employs many modules for unique patterns and a single DNN-AM network for feature extraction and classification. By employing a Local Binary Pattern image for analysis, the feature set is expanded, improving the extraction of ADHD patterns in children. The suggested method, DNN-AM, outperforms the trained network in predicting ADHD in children, obtaining the lowest error rate, higher accuracy, and F1-Score. With both learning models, RF and DNN-AM the ADHD in children is diagnosed. © 2024 IEEE.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Live Audio Recognition and Text Conversion System 2

Live Audio Recognition and Text Conversion System

引用

2nd International Conference on Computational Intelligence, Communication technology and Networking, CICTN 2025

作者： Sharma, Pratyaksha Gupta, Sumita Bhavya, Boddu Asmitha Sharma, Khushi Dhir, Saru Gambhir, Sapna Department of Computer Science & Engineering Amity School of Engineering & Technology Amity University UP India Department of Information Technology Amity School of Engineering & Technology Amity University UP India Dept. of Computer Science College of Engineering and Computing George Mason University United States

ISBN: (纸本)9798331530389

With the advancement of technologies, different methods are currently being used for converting spoken language into text. These systems offer a hands-free alternative to traditional input methods, especially for individuals with physical disabilities or those requiring efficient documentation of spoken content. The goal of this study is to review recent advancements in this field and highlight gaps in current research, with a focus on accuracy, language adaptability, ease of use, and the integration of various technologies. We also suggest future directions for enhancing and developing this technology further. © 2025 IEEE.

关键词： Hidden Markov models

来源：评论

学校读者我要写书评

暂无评论

Novel Approach to Monitor Location of the Student in the Institution 15

Novel Approach to Monitor Location of the Student in the Ins...

引用

15th International Conference on Advances in Computing, Control, and Telecommunication Technologies, ACT 2024

作者： Kulkarni, R.N. Suma, Rochana Y. Sravanthi, B. Rakshitha, G. Krathika, T. Ballari Institute of Technology and Management Dept. of Computer Science & Engineering Ballari India

ISBN: (纸本)9798331300579

During the last few decades there is a tremendous growth in the information and communication technology wherein many organizations are making use of the hardware and software for various applications. Marking the attendance of a student in the school or college as well as the presence of the employee in the workplace is to be either captured or manually marked in the registers. Performing various analyses by taking the manual input is cumbersome because the number of students in the class or number of employees in the organizations are increasing. To overcome the difficulties of managing the things manually in this paper we are proposing an automated tool to capture the presence of the student in the specific location. This paper proposes a novel approach to mark the presence of a student in the college premises. The tool developed here is an Android Application (App) wherein the students can send the details to the App. Two modules are proposed here, one for the student and another for the Administrator. Through the student module, each student can login to the App and capture the self-image and send it to the Administrator Module. The captured image comprises the GPS details like Longitude, Latitude, Time, and date information. The information sent through the App determines the location of the student whether the student is in the college premise such as Class room, Laboratory and Library. The application which is managed by the teacher or the administrator or proctor will get the details about the student's image, GPS locations such as latitude, longitude, date and time. The mobile app verifies the GPS location and image of the student and compares it with the database. If the captured information matches with the appropriate GPS location then the students attendance is marked as present in that particular duration and appropriate files are updated. © Grenze Scientific Society, 2024.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

A Deep Learning Approach to Enhance Air Quality Prediction: Comparative Analysis of LSTM, LSTM with Attention Mechanism and BiLSTM

A Deep Learning Approach to Enhance Air Quality Prediction: ...

引用

2024 IEEE Region 10 Symposium, TENSYMP 2024

作者： Bhardwaj, Deepanshu Ragiri, Prakash Rao Netaji Subhas University of Technology Dept. of Computer Science and Engineering Delhi India

ISBN: (纸本)9798350364866

In this study, we address the challenge of predicting air quality indices (AQIs) by leveraging Long Short-Term Memory (LSTM) networks. Recognizing the dynamic nature of air quality data, we explore the efficacy of three LSTM variants - standard LSTM, LSTM with an attention mechanism, and Bidirectional LSTM (BiLSTM) - in capturing temporal dependencies and improving forecast accuracy. Our methodology involved preprocessing a comprehensive dataset of air quality measures, followed by an experimental design that tested each model variant under different sequence lengths (30 and 365 days). The models were evaluated based on their mean squared error (MSE), root mean squared error (RMSE), and mean absolute error (MAE) across three response variables: Nitrogen Oxides (NO), Particulate Matter up to 10 micrometers in size (PM10), and Particulate Matter up to 2.5 micrometers in size (PM2.5). Notably, when comparing the RMSE values across the three models, the LSTM with the attention mechanism consistently outperformed the standard LSTM and BiLSTM models, particularly with a sequence length of 30 days, indicating a superior ability to capture the intricacies of temporal dependencies in environmental data. Moreover, the shorter sequence length generally yielded better predictive performance, suggesting that longer sequences might introduce unnecessary complexity or overfitting. These indications of our study suggest a promising direction for the deployment of attention-based models in real-time AQI prediction systems, which could enhance the accuracy of environmental forecasts and inform public health decisions more effectively. Future work will explore the integration of additional environmental factors, the refinement of model frameworks, and the expansion of the dataset to include multi-city comparisons. © 2024 IEEE.

关键词： Mean square error

来源：评论

学校读者我要写书评

暂无评论

Effective Polyp Segmentation in Medical Imaging: A Semi-Supervised Approach with Progressive Supervision 3

Effective Polyp Segmentation in Medical Imaging: A Semi-Supe...

引用

3rd International Conference on Big Data, Information and computer Network, BDICN 2024

作者： Ye, Shunlong Ji, Zexuan Nanjing University of Science and Technology Dept. of Computer Science and Engineering Nanjing China

ISBN: (纸本)9798350363821

Medical imaging plays a pivotal role in diagnosing and monitoring various diseases, and accurate polyp segmentation is essential for early disease detection and treatment planning. However, the scarcity of well-Annotated medical imaging data hampers the development of effective segmentation models. Semi-supervised learning stands out as a critical approach to address this issue. Traditional semi-supervised medical image segmentation models leverage strong-weak perturbation consistency losses to provide supervision signals. While these losses are effective in promoting consistency, they often exhibit a drawback, that is the dominance of strong perturbations during early training stages. This dominance hinders the model's ability to extract meaningful features, ultimately impacting its overall performance. In response to these challenges, we introduce a novel training method applied to polyp segmentation. We employ a progressive approach, gradually introducing strong-weak perturbation supervision signals. This gradual guidance empowers the model to focus on learning relevant features from the beginning of training, mitigating the issue of early dominance and enhancing its performance. Our method is evaluated on two widely-used polyp segmentation datasets and surpasses state-of-The-Art methods, demonstrating substantial improvements in segmentation accuracy. © 2024 IEEE.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Remote Sensing–Based UAV Imaging in Heat Pattern Analysis Impact on Climate Change Detection Using Fuzzy Stacked Lasso Elastic-Net Model

引用

Remote Sensing in Earth Systems Sciences 2024年第4期7卷 699-708页

作者： Sailaja, M. Kumar, M. Prema Jyothi, B. Swarna Vanguri, G. L. Narasamba Manjula, S. Priya, D. Divya Department of Computer Science and Engineering Ravindra College of Engineering for Women Andhra Pradesh Kurnool India Dept. of ECE Shri Vishnu Engineering College for Women (A) Andhra Pradesh Bhimavaram 534202 India Department of Computer Science & amp Engineering Madanapalle Institute of Technology & amp Science Andhra Pradesh Madanapalle India Information Technology Aditya College of Engineering & amp Technology(A) Andhra Pradesh Surampalem 533437 India Department of Computer Science and Business Systems Nehru Institute of Engineering and Technology Coimbatore India Department of Computer Science and Engineering MLR Institute of Technology Hyderabad India

Urban heat islands raise surface temperatures, which has an effect on city dwellers’ health and welfare. Urbanisation-related changes to the land surface, which are especially notable right after sunset, have an impact on radiative forcing. Recently, there has been a surge in the usage of unmanned aerial vehicle (UAV) technology, particularly for precision agriculture and plant phenotyping. This is due to the declining cost and increased accessibility of both UAVs and thermal imaging sensors. This interruption affects subsequent operations like target item categorisation and water quality parameter inversion. The goal of this study was to evaluate the potential for combining machine learning (ML) with unmanned aerial vehicle (UAV)–based imaging technology. In this research, the novel technique in UAV image–based temperature pattern detection of various regions of earth and their sea level rise analysis using image classification by machine learning model. Here, the input is collected as UAV images which have been processed for noise removal and normalisation. These image features have been extracted using convolutional active contour–based kernel component analysis and classified using region-based fuzzy stacked lasso elastic-net model. The classified output shows temperature analysis with sea level rise based on image analysis. The experimental analysis has been carried out for various UAV image dataset in terms of detection accuracy, RMSE, F-measure, mean average precision (MAP), and recall. Proposed technique F-measure of 89%, detection accuracy of 96%, MAP of 94%, recall of 92%, and RMSE of 60%. © The Author(s), under exclusive licence to Springer Nature Switzerland AG 2024.

关键词： Convolutional active contour Heat pattern detection Kernel component analysis Lasso elastic-net model Remote sensing

来源：评论

学校读者我要写书评

暂无评论

Relocation Service Provider Application 3

Relocation Service Provider Application

引用

3rd International Conference for Innovation in technology, INOCON 2024

作者： Shobha, Shobha Choudhary, Ankita Kour, Naindeep Prakash, Nitin Tejas, P.R. Nitte Meenakshi Institute of Technology Dept. of Computer Science and Engineering Bengaluru India

ISBN: (纸本)9798350381931

This research aims to solve many problems people face when moving to a new place, such as housing, food, transportation, language differences and optimization. By creating recommendations, it is aimed to provide self-support to facilitate the transition process. The system will consider people's interests and consider different languages and cultures and budgets of people. This is useful in war or disaster environment. © 2024 IEEE.

关键词： Budget control

来源：评论

学校读者我要写书评

暂无评论

AI-Based Indian Currency Detection for Visually Challenged Users

AI-Based Indian Currency Detection for Visually Challenged U...

引用

2024 International Conference on System, Computation, Automation and Networking, ICSCAN 2024

作者： Shopika, S. Senthil Velan, A.S. Dharun Prakash, S.R. Pavithra, S. Lakshmi, R Poornima Ponnusamy, R. Chennai Institute of Technology Dept. of Computer Science and Engineering Tamilnadu Chennai India

ISBN: (纸本)9798331510022

For denomination recognition, this Indian Currency Detection System will use a CNN trained on an extremely large and diverse set of Indian banknotes from 10 to 2000. It possesses an amicable interface through which images can be captured using the camera of the user's smartphone, providing real-time audio feedback to denominate the banknote without requiring any visual assistance. Made with the features of capturing an image, real-time recognition, and user-friendly design, these are made to add a great experience for smooth navigation by a blind person. The novel and innovative features make this Indian Currency Detection System unique. Using CNN, which has been trained on the comprehensive set of Indian banknotes from 10 to 2000, the software lets a user capture banknote image directly by the smartphone camera. It allows knowing the denomination through real-time audio feedback without any visual assistance. Such characteristics include image capture, real-time identification, and designing user-friendly user interfaces that make easy navigation of the surroundings possible for the visually impaired. It does more than detect currency. It significantly contributes to the discussion regarding the development and availability of more assistive technologies. It is usable and aims to bring about greater accessibility and inclusivity in promoting financial independence among visually impaired people. Contributing to the ability of cash transactions among the visually impaired to gain confidence in freedom and security, this project aligns with a broader discussion related to assistive technologies. © 2024 IEEE.

关键词： Assistive technology

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：